state: generation 10810 (intent)
This commit is contained in:
@@ -163,7 +163,7 @@
|
||||
"ascend_910-b3|vllm|text-generation|model_type:qwen3_5": {
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectures": [],
|
||||
"evidenceCount": 11,
|
||||
"evidenceCount": 10,
|
||||
"expiresAt": "2026-10-20T11:23:21+00:00",
|
||||
"framework": "vllm",
|
||||
"latestFailureAt": "2026-09-20T11:23:21+00:00",
|
||||
@@ -806,6 +806,25 @@
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|model_type:qwen3_5_moe": {
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectures": [],
|
||||
"evidenceCount": 1,
|
||||
"expiresAt": "2026-10-20T02:52:52.043508+00:00",
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"latestFailureAt": "2026-09-20T02:52:52.043508+00:00",
|
||||
"latestSuccessfulAt": null,
|
||||
"matchType": "model_type",
|
||||
"modelType": "qwen3_5_moe",
|
||||
"sourceModelIds": [
|
||||
"mlx-community/XYZ-Aquila-mini-OptiQ-4bit"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"4969075"
|
||||
],
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|model_type:zaya": {
|
||||
"architectureSignature": "model_type:zaya",
|
||||
"architectures": [],
|
||||
@@ -889,26 +908,26 @@
|
||||
"hygon_k100-ai|vllm|text-generation|model_type:qwen3_5": {
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectures": [],
|
||||
"evidenceCount": 5,
|
||||
"expiresAt": "2026-10-17T10:05:21+00:00",
|
||||
"evidenceCount": 6,
|
||||
"expiresAt": "2026-10-20T18:51:21+00:00",
|
||||
"framework": "vllm",
|
||||
"latestFailureAt": "2026-09-17T10:05:21+00:00",
|
||||
"latestFailureAt": "2026-09-20T18:51:21+00:00",
|
||||
"latestSuccessfulAt": null,
|
||||
"matchType": "model_type",
|
||||
"modelType": "qwen3_5",
|
||||
"sourceModelIds": [
|
||||
"logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired",
|
||||
"ewinregirgojr/Qwen3.8-14B-Instruct-Turbo",
|
||||
"VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU",
|
||||
"EschaLabs/Qwen3.8-27B-Escha-W2",
|
||||
"douyamv/Qwen3.8-27B-FP8",
|
||||
"cyankiwi/Ornith-1.5-9B-AWQ-FP8"
|
||||
"douyamv/Qwen3.8-27B-FP8"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"4523697",
|
||||
"4490374",
|
||||
"4460362",
|
||||
"4595432",
|
||||
"4609095",
|
||||
"4592744"
|
||||
"4609095"
|
||||
],
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation"
|
||||
@@ -2127,9 +2146,9 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-20T18:36:43.496076+00:00",
|
||||
"generatedAt": "2026-09-20T18:53:02.260239+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 104,
|
||||
"activeBlockCount": 105,
|
||||
"byGpuFramework": {
|
||||
"Ascend_910-b3|vllm": 11,
|
||||
"Ascend_910-b3|vllm_tokenizer_patch": 2,
|
||||
@@ -2148,7 +2167,7 @@
|
||||
"Vastai_va16|vllm": 16,
|
||||
"Vastai_va16|vllm_fix_tokenizer": 2,
|
||||
"hygon_k100-ai|vllm": 8,
|
||||
"hygon_k100-ai|vllm-patch-tokenizer": 2
|
||||
"hygon_k100-ai|vllm-patch-tokenizer": 3
|
||||
},
|
||||
"ttlDays": 30
|
||||
}
|
||||
|
||||
@@ -425,7 +425,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-20T18:51:36.359381+00:00",
|
||||
"generatedAt": "2026-09-20T18:53:14.969111+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-20T18:36:43.439931+00:00",
|
||||
"lastSyncTime": "2026-09-20T18:36:43.146458+00:00",
|
||||
"generatedAt": "2026-09-20T18:53:14.902838+00:00",
|
||||
"lastSyncTime": "2026-09-20T18:53:14.846163+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -167,7 +167,7 @@
|
||||
"ascend_910-b3|vllm|text-generation|model_type:qwen3_5": {
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectures": [],
|
||||
"evidenceCount": 11,
|
||||
"evidenceCount": 10,
|
||||
"expiresAt": "2026-10-20T11:23:21+00:00",
|
||||
"framework": "vllm",
|
||||
"latestFailureAt": "2026-09-20T11:23:21+00:00",
|
||||
@@ -810,6 +810,25 @@
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|model_type:qwen3_5_moe": {
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectures": [],
|
||||
"evidenceCount": 1,
|
||||
"expiresAt": "2026-10-20T02:52:52.043508+00:00",
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"latestFailureAt": "2026-09-20T02:52:52.043508+00:00",
|
||||
"latestSuccessfulAt": null,
|
||||
"matchType": "model_type",
|
||||
"modelType": "qwen3_5_moe",
|
||||
"sourceModelIds": [
|
||||
"mlx-community/XYZ-Aquila-mini-OptiQ-4bit"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"4969075"
|
||||
],
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|model_type:zaya": {
|
||||
"architectureSignature": "model_type:zaya",
|
||||
"architectures": [],
|
||||
@@ -893,26 +912,26 @@
|
||||
"hygon_k100-ai|vllm|text-generation|model_type:qwen3_5": {
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectures": [],
|
||||
"evidenceCount": 5,
|
||||
"expiresAt": "2026-10-17T10:05:21+00:00",
|
||||
"evidenceCount": 6,
|
||||
"expiresAt": "2026-10-20T18:51:21+00:00",
|
||||
"framework": "vllm",
|
||||
"latestFailureAt": "2026-09-17T10:05:21+00:00",
|
||||
"latestFailureAt": "2026-09-20T18:51:21+00:00",
|
||||
"latestSuccessfulAt": null,
|
||||
"matchType": "model_type",
|
||||
"modelType": "qwen3_5",
|
||||
"sourceModelIds": [
|
||||
"logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired",
|
||||
"ewinregirgojr/Qwen3.8-14B-Instruct-Turbo",
|
||||
"VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU",
|
||||
"EschaLabs/Qwen3.8-27B-Escha-W2",
|
||||
"douyamv/Qwen3.8-27B-FP8",
|
||||
"cyankiwi/Ornith-1.5-9B-AWQ-FP8"
|
||||
"douyamv/Qwen3.8-27B-FP8"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"4523697",
|
||||
"4490374",
|
||||
"4460362",
|
||||
"4595432",
|
||||
"4609095",
|
||||
"4592744"
|
||||
"4609095"
|
||||
],
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation"
|
||||
@@ -2132,7 +2151,7 @@
|
||||
}
|
||||
},
|
||||
"architectureCompatibilitySummary": {
|
||||
"activeBlockCount": 104,
|
||||
"activeBlockCount": 105,
|
||||
"byGpuFramework": {
|
||||
"Ascend_910-b3|vllm": 11,
|
||||
"Ascend_910-b3|vllm_tokenizer_patch": 2,
|
||||
@@ -2151,7 +2170,7 @@
|
||||
"Vastai_va16|vllm": 16,
|
||||
"Vastai_va16|vllm_fix_tokenizer": 2,
|
||||
"hygon_k100-ai|vllm": 8,
|
||||
"hygon_k100-ai|vllm-patch-tokenizer": 2
|
||||
"hygon_k100-ai|vllm-patch-tokenizer": 3
|
||||
},
|
||||
"ttlDays": 30
|
||||
},
|
||||
@@ -2429,10 +2448,10 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 12,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 19,
|
||||
"ambiguous_runtime": 20,
|
||||
"framework_architecture_unsupported": 12
|
||||
},
|
||||
"failureCount": 31,
|
||||
"failureCount": 32,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"pendingCount": 0,
|
||||
@@ -2442,8 +2461,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 31,
|
||||
"unresolvedFailureCount": 19
|
||||
"total": 32,
|
||||
"unresolvedFailureCount": 20
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation": {
|
||||
"attributableFailureCount": 199,
|
||||
@@ -3875,10 +3894,10 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation": {
|
||||
"attributableFailureCount": 619,
|
||||
"decisionFailureRate": 0.9642,
|
||||
"decisionSuccessRate": 0.0358,
|
||||
"decisionTotal": 642,
|
||||
"attributableFailureCount": 621,
|
||||
"decisionFailureRate": 0.9643,
|
||||
"decisionSuccessRate": 0.0357,
|
||||
"decisionTotal": 644,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 127,
|
||||
"architecture_compatibility": 20,
|
||||
@@ -3886,13 +3905,14 @@
|
||||
"context_length": 46,
|
||||
"framework_architecture_unsupported": 192,
|
||||
"memory_capacity": 84,
|
||||
"model_load": 58,
|
||||
"model_load": 59,
|
||||
"platform_infrastructure": 3,
|
||||
"repository_structure": 98,
|
||||
"runtime_memory": 1,
|
||||
"tokenizer_compatibility": 78,
|
||||
"参数/模板问题": 9
|
||||
},
|
||||
"failureCount": 758,
|
||||
"failureCount": 760,
|
||||
"failureRate": 0.9706,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -3902,7 +3922,7 @@
|
||||
"successRate": 0.0294,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 781,
|
||||
"total": 783,
|
||||
"unresolvedFailureCount": 136
|
||||
},
|
||||
"MetaX_c-500|vllm|unknown": {
|
||||
@@ -4513,18 +4533,18 @@
|
||||
"unresolvedFailureCount": 72
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
|
||||
"attributableFailureCount": 20,
|
||||
"attributableFailureCount": 22,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 20,
|
||||
"decisionTotal": 22,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 12,
|
||||
"framework_architecture_unsupported": 13,
|
||||
"model_load": 1,
|
||||
"framework_architecture_unsupported": 14,
|
||||
"model_load": 2,
|
||||
"runtime_memory": 6,
|
||||
"参数/模板问题": 8
|
||||
},
|
||||
"failureCount": 40,
|
||||
"failureCount": 42,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"pendingCount": 0,
|
||||
@@ -4534,20 +4554,20 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 40,
|
||||
"total": 42,
|
||||
"unresolvedFailureCount": 20
|
||||
},
|
||||
"hygon_k100-ai|vllm|text-generation": {
|
||||
"attributableFailureCount": 648,
|
||||
"attributableFailureCount": 649,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 648,
|
||||
"decisionTotal": 649,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 153,
|
||||
"architecture_compatibility": 30,
|
||||
"attention_backend": 1,
|
||||
"context_length": 42,
|
||||
"framework_architecture_unsupported": 221,
|
||||
"framework_architecture_unsupported": 222,
|
||||
"memory_capacity": 58,
|
||||
"model_load": 56,
|
||||
"platform_infrastructure": 3,
|
||||
@@ -4555,7 +4575,7 @@
|
||||
"runtime_memory": 52,
|
||||
"tokenizer_compatibility": 79
|
||||
},
|
||||
"failureCount": 804,
|
||||
"failureCount": 805,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -4565,7 +4585,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 804,
|
||||
"total": 805,
|
||||
"unresolvedFailureCount": 153
|
||||
},
|
||||
"hygon_k100-ai|vllm|unknown": {
|
||||
@@ -4689,33 +4709,33 @@
|
||||
"unresolvedFailureCount": 6406
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 3487,
|
||||
"attributableFailureCount": 3490,
|
||||
"decisionFailureRate": 0.977,
|
||||
"decisionSuccessRate": 0.023,
|
||||
"decisionTotal": 3569,
|
||||
"decisionTotal": 3572,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1440,
|
||||
"architecture_compatibility": 112,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 84,
|
||||
"context_length": 161,
|
||||
"framework_architecture_unsupported": 1271,
|
||||
"framework_architecture_unsupported": 1272,
|
||||
"memory_capacity": 720,
|
||||
"model_load": 199,
|
||||
"model_load": 200,
|
||||
"platform_infrastructure": 864,
|
||||
"repository_structure": 470,
|
||||
"runtime_memory": 60,
|
||||
"runtime_memory": 61,
|
||||
"tokenizer_compatibility": 409,
|
||||
"参数/模板问题": 40
|
||||
},
|
||||
"failureCount": 5831,
|
||||
"failureCount": 5834,
|
||||
"failureRate": 0.9861,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 864,
|
||||
"successCount": 82,
|
||||
"successRate": 0.0139,
|
||||
"total": 5913,
|
||||
"total": 5916,
|
||||
"unresolvedFailureCount": 1480
|
||||
},
|
||||
"vllm-customized": {
|
||||
@@ -4759,25 +4779,25 @@
|
||||
"unresolvedFailureCount": 48
|
||||
},
|
||||
"vllm-patch-tokenizer": {
|
||||
"attributableFailureCount": 20,
|
||||
"attributableFailureCount": 22,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 20,
|
||||
"decisionTotal": 22,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 12,
|
||||
"framework_architecture_unsupported": 13,
|
||||
"model_load": 1,
|
||||
"framework_architecture_unsupported": 14,
|
||||
"model_load": 2,
|
||||
"runtime_memory": 6,
|
||||
"参数/模板问题": 8
|
||||
},
|
||||
"failureCount": 40,
|
||||
"failureCount": 42,
|
||||
"failureRate": 1.0,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"total": 40,
|
||||
"total": 42,
|
||||
"unresolvedFailureCount": 20
|
||||
},
|
||||
"vllm_0_17_0_corex_4_4_0": {
|
||||
@@ -4835,22 +4855,22 @@
|
||||
"decisionSuccessRate": 0.0606,
|
||||
"decisionTotal": 33,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 31,
|
||||
"ambiguous_runtime": 32,
|
||||
"framework_architecture_unsupported": 30,
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 62,
|
||||
"failureRate": 0.9688,
|
||||
"failureCount": 63,
|
||||
"failureRate": 0.9692,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0312,
|
||||
"total": 64,
|
||||
"unresolvedFailureCount": 31
|
||||
"successRate": 0.0308,
|
||||
"total": 65,
|
||||
"unresolvedFailureCount": 32
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-20T18:36:43.430657+00:00",
|
||||
"generatedAt": "2026-09-20T18:53:14.894277+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 78,
|
||||
@@ -4883,7 +4903,7 @@
|
||||
"decisionSuccessRate": 0.1689,
|
||||
"decisionTotal": 367,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 147,
|
||||
"ambiguous_runtime": 148,
|
||||
"context_length": 1,
|
||||
"framework_architecture_unsupported": 165,
|
||||
"memory_capacity": 18,
|
||||
@@ -4895,15 +4915,15 @@
|
||||
"日志缺失": 14,
|
||||
"验证失败": 175
|
||||
},
|
||||
"failureCount": 896,
|
||||
"failureCount": 897,
|
||||
"failureRate": 0.9353,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 62,
|
||||
"successRate": 0.0647,
|
||||
"total": 958,
|
||||
"unresolvedFailureCount": 590
|
||||
"total": 959,
|
||||
"unresolvedFailureCount": 591
|
||||
},
|
||||
"Biren_166m": {
|
||||
"attributableFailureCount": 175,
|
||||
@@ -5116,10 +5136,10 @@
|
||||
"unresolvedFailureCount": 170
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"attributableFailureCount": 654,
|
||||
"decisionFailureRate": 0.8195,
|
||||
"decisionSuccessRate": 0.1805,
|
||||
"decisionTotal": 798,
|
||||
"attributableFailureCount": 656,
|
||||
"decisionFailureRate": 0.82,
|
||||
"decisionSuccessRate": 0.18,
|
||||
"decisionTotal": 800,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 299,
|
||||
"architecture_compatibility": 21,
|
||||
@@ -5127,22 +5147,23 @@
|
||||
"context_length": 59,
|
||||
"framework_architecture_unsupported": 196,
|
||||
"memory_capacity": 85,
|
||||
"model_load": 58,
|
||||
"model_load": 59,
|
||||
"platform_infrastructure": 5,
|
||||
"repository_structure": 114,
|
||||
"runtime_memory": 1,
|
||||
"tokenizer_compatibility": 78,
|
||||
"参数/模板问题": 398,
|
||||
"日志缺失": 15,
|
||||
"验证失败": 48
|
||||
},
|
||||
"failureCount": 1419,
|
||||
"failureRate": 0.9079,
|
||||
"failureCount": 1421,
|
||||
"failureRate": 0.908,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 5,
|
||||
"successCount": 144,
|
||||
"successRate": 0.0921,
|
||||
"total": 1563,
|
||||
"successRate": 0.092,
|
||||
"total": 1565,
|
||||
"unresolvedFailureCount": 760
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
@@ -5231,18 +5252,18 @@
|
||||
"unresolvedFailureCount": 1303
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"attributableFailureCount": 683,
|
||||
"decisionFailureRate": 0.9579,
|
||||
"decisionSuccessRate": 0.0421,
|
||||
"decisionTotal": 713,
|
||||
"attributableFailureCount": 686,
|
||||
"decisionFailureRate": 0.9581,
|
||||
"decisionSuccessRate": 0.0419,
|
||||
"decisionTotal": 716,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 298,
|
||||
"architecture_compatibility": 32,
|
||||
"attention_backend": 1,
|
||||
"context_length": 46,
|
||||
"framework_architecture_unsupported": 236,
|
||||
"framework_architecture_unsupported": 238,
|
||||
"memory_capacity": 58,
|
||||
"model_load": 57,
|
||||
"model_load": 58,
|
||||
"platform_infrastructure": 4,
|
||||
"repository_structure": 116,
|
||||
"runtime_memory": 58,
|
||||
@@ -5251,14 +5272,14 @@
|
||||
"日志缺失": 66,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 1454,
|
||||
"failureCount": 1457,
|
||||
"failureRate": 0.9798,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 4,
|
||||
"successCount": 30,
|
||||
"successRate": 0.0202,
|
||||
"total": 1484,
|
||||
"total": 1487,
|
||||
"unresolvedFailureCount": 767
|
||||
}
|
||||
},
|
||||
@@ -5279,7 +5300,7 @@
|
||||
"hygon_k100-ai": 64.0
|
||||
},
|
||||
"pendingRecords": 0,
|
||||
"policyCancelledRecords": 125,
|
||||
"policyCancelledRecords": 134,
|
||||
"profileCombinationStats": {
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|cohere2|none": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -5762,6 +5783,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma2|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"modelType": "gemma2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -11826,6 +11870,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|lfm2|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"modelType": "lfm2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|awq": {
|
||||
"attributableFailureCount": 2,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -11944,6 +12011,29 @@
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_moe|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"modelType": "qwen3_5_moe",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_text|none": {
|
||||
"attributableFailureCount": 2,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -12138,18 +12228,18 @@
|
||||
"unresolvedFailureCount": 5
|
||||
},
|
||||
"Ascend_910-b3|vllm|text-generation": {
|
||||
"attributableFailureCount": 15,
|
||||
"consecutiveFailures": 15,
|
||||
"attributableFailureCount": 14,
|
||||
"consecutiveFailures": 14,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 15,
|
||||
"decisionTotal": 14,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 5,
|
||||
"framework_architecture_unsupported": 14,
|
||||
"framework_architecture_unsupported": 13,
|
||||
"tokenizer_compatibility": 1
|
||||
},
|
||||
"failureCount": 20,
|
||||
"failureCount": 19,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -12161,7 +12251,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 20,
|
||||
"total": 19,
|
||||
"unresolvedFailureCount": 5
|
||||
},
|
||||
"Ascend_910-b4|unknown|text-generation": {
|
||||
@@ -12197,9 +12287,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2
|
||||
"ambiguous_runtime": 3
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -12211,21 +12301,21 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation": {
|
||||
"attributableFailureCount": 9,
|
||||
"consecutiveFailures": 9,
|
||||
"attributableFailureCount": 8,
|
||||
"consecutiveFailures": 8,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 9,
|
||||
"decisionTotal": 8,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 6,
|
||||
"framework_architecture_unsupported": 9
|
||||
"ambiguous_runtime": 5,
|
||||
"framework_architecture_unsupported": 8
|
||||
},
|
||||
"failureCount": 15,
|
||||
"failureCount": 13,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -12237,8 +12327,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 15,
|
||||
"unresolvedFailureCount": 6
|
||||
"total": 13,
|
||||
"unresolvedFailureCount": 5
|
||||
},
|
||||
"Biren_166m|unknown|text-generation": {
|
||||
"attributableFailureCount": 9,
|
||||
@@ -12541,9 +12631,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 9
|
||||
"ambiguous_runtime": 8
|
||||
},
|
||||
"failureCount": 9,
|
||||
"failureCount": 8,
|
||||
"failureRate": 1.0,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -12555,8 +12645,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 9,
|
||||
"unresolvedFailureCount": 9
|
||||
"total": 8,
|
||||
"unresolvedFailureCount": 8
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -12634,23 +12724,25 @@
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation": {
|
||||
"attributableFailureCount": 3,
|
||||
"consecutiveFailures": 3,
|
||||
"attributableFailureCount": 5,
|
||||
"consecutiveFailures": 5,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 3,
|
||||
"decisionTotal": 5,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3,
|
||||
"backend_operator": 1,
|
||||
"framework_architecture_unsupported": 1,
|
||||
"model_load": 1,
|
||||
"runtime_memory": 1,
|
||||
"tokenizer_compatibility": 1
|
||||
},
|
||||
"failureCount": 6,
|
||||
"failureCount": 8,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-20T16:40:51.571551+00:00",
|
||||
"lastTerminalAt": "2026-09-20T18:53:01.473044+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -12658,7 +12750,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 6,
|
||||
"total": 8,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Mthreads_s4000|unknown|text-generation": {
|
||||
@@ -12895,22 +12987,22 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"hygon_k100-ai|vllm|text-generation": {
|
||||
"attributableFailureCount": 9,
|
||||
"consecutiveFailures": 9,
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
|
||||
"attributableFailureCount": 2,
|
||||
"consecutiveFailures": 2,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 9,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 6,
|
||||
"framework_architecture_unsupported": 9
|
||||
"framework_architecture_unsupported": 1,
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 15,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-20T16:12:47.264764+00:00",
|
||||
"lastTerminalAt": "2026-09-20T18:53:01.473025+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -12918,7 +13010,33 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 15,
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"hygon_k100-ai|vllm|text-generation": {
|
||||
"attributableFailureCount": 10,
|
||||
"consecutiveFailures": 10,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 10,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 6,
|
||||
"framework_architecture_unsupported": 10
|
||||
},
|
||||
"failureCount": 16,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-20T18:53:01.472996+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 16,
|
||||
"unresolvedFailureCount": 6
|
||||
}
|
||||
},
|
||||
@@ -13123,6 +13241,31 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma2|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"lastTerminalAt": "2026-09-20T18:53:01.473054+00:00",
|
||||
"modelType": "gemma2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
@@ -15150,6 +15293,56 @@
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|lfm2|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"lastTerminalAt": "2026-09-20T18:53:01.473025+00:00",
|
||||
"modelType": "lfm2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_moe|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"lastTerminalAt": "2026-09-20T18:53:01.473075+00:00",
|
||||
"modelType": "qwen3_5_moe",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"sizedProfileCombinationStats": {
|
||||
@@ -15865,6 +16058,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma2|none|34": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"loadSizeLog2Bucket": 34,
|
||||
"modelType": "gemma2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2|none|29": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -24882,6 +25099,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|lfm2|none|29": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"loadSizeLog2Bucket": 29,
|
||||
"modelType": "lfm2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|awq|30": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -25052,6 +25293,30 @@
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_moe|none|35": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"loadSizeLog2Bucket": 35,
|
||||
"modelType": "qwen3_5_moe",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_text|none|32": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -25270,39 +25535,39 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 15930,
|
||||
"totalRecords": 16055,
|
||||
"terminalRecords": 15936,
|
||||
"totalRecords": 16070,
|
||||
"totals": {
|
||||
"attributableFailureCount": 5780,
|
||||
"decisionFailureRate": 0.8613,
|
||||
"decisionSuccessRate": 0.1387,
|
||||
"decisionTotal": 6711,
|
||||
"attributableFailureCount": 5785,
|
||||
"decisionFailureRate": 0.8614,
|
||||
"decisionSuccessRate": 0.1386,
|
||||
"decisionTotal": 6716,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3795,
|
||||
"ambiguous_runtime": 3796,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 102,
|
||||
"context_length": 318,
|
||||
"framework_architecture_unsupported": 2004,
|
||||
"framework_architecture_unsupported": 2006,
|
||||
"memory_capacity": 1196,
|
||||
"model_load": 480,
|
||||
"model_load": 482,
|
||||
"platform_infrastructure": 922,
|
||||
"repository_structure": 734,
|
||||
"runtime_memory": 78,
|
||||
"runtime_memory": 79,
|
||||
"tokenizer_compatibility": 655,
|
||||
"参数/模板问题": 3110,
|
||||
"日志缺失": 719,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 14999,
|
||||
"failureCount": 15005,
|
||||
"failureRate": 0.9416,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 922,
|
||||
"successCount": 931,
|
||||
"successRate": 0.0584,
|
||||
"total": 15930,
|
||||
"unresolvedFailureCount": 8297
|
||||
"total": 15936,
|
||||
"unresolvedFailureCount": 8298
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
@@ -25353,6 +25618,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 16055,
|
||||
"summarizedRecords": 16070,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -14,13 +14,13 @@
|
||||
100
|
||||
],
|
||||
"accounts": 12,
|
||||
"activeScanned": 1149,
|
||||
"activeScanned": 1143,
|
||||
"ageCleanupMode": "admission_only",
|
||||
"agePolicySkipped": {
|
||||
"cleanupDisabled": true,
|
||||
"reason": "admission_only"
|
||||
},
|
||||
"architectureBlockCount": 104,
|
||||
"architectureBlockCount": 105,
|
||||
"architectureFrameworkCatalog": {
|
||||
"ascend_910-b3|text-generation": [
|
||||
"llamacpp",
|
||||
@@ -71,237 +71,195 @@
|
||||
]
|
||||
},
|
||||
"architectureFrameworkCatalogErrors": {},
|
||||
"architectureIncompatibleCount": 11,
|
||||
"architectureIncompatibleCount": 9,
|
||||
"architectureIncompatibleTasks": [
|
||||
{
|
||||
"accountIndex": 1,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:51.297854+00:00",
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:52.043508+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
"model_type:qwen3_5_moe"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
"vllm-patch-tokenizer"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Kunlunxin_p-800",
|
||||
"modelId": "EschaLabs/Qwen3.8-27B-Escha-W2",
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"gpuType": "hygon_k100-ai",
|
||||
"modelId": "primitive-ai/Nex-N2.5-mini-FP8",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4969333,
|
||||
"taskId": 4754068,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 2,
|
||||
"accountIndex": 3,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:51.297854+00:00",
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:52.043508+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
"model_type:qwen3_5_moe"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
"vllm-patch-tokenizer"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Kunlunxin_p-800",
|
||||
"modelId": "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo",
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"gpuType": "hygon_k100-ai",
|
||||
"modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4969326,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 2,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:51.297854+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Kunlunxin_p-800",
|
||||
"modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4970000,
|
||||
"taskId": 4969661,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 4,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:51.297854+00:00",
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:52.043508+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
"model_type:qwen3_5_moe"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
"vllm-patch-tokenizer"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Kunlunxin_p-800",
|
||||
"modelId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo",
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"gpuType": "hygon_k100-ai",
|
||||
"modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4969328,
|
||||
"taskId": 4849006,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 5,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:51.297854+00:00",
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:52.043508+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
"model_type:qwen3_5_moe"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
"vllm-patch-tokenizer"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Kunlunxin_p-800",
|
||||
"modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit",
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"gpuType": "hygon_k100-ai",
|
||||
"modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4969043,
|
||||
"taskId": 4923872,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 5,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:52.043508+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5_moe"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm-patch-tokenizer"
|
||||
],
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"gpuType": "hygon_k100-ai",
|
||||
"modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4939007,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 7,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:51.297854+00:00",
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:52.043508+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
"model_type:qwen3_5_moe"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
"vllm-patch-tokenizer"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Kunlunxin_p-800",
|
||||
"modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw",
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"gpuType": "hygon_k100-ai",
|
||||
"modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4969331,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 8,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:51.297854+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Kunlunxin_p-800",
|
||||
"modelId": "ornith-ai/Ornith-1.5-9B-NVFP4",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4969322,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 8,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:51.297854+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Kunlunxin_p-800",
|
||||
"modelId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4969332,
|
||||
"taskId": 4795634,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 10,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:51.297854+00:00",
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:52.043508+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
"model_type:qwen3_5_moe"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
"vllm-patch-tokenizer"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Kunlunxin_p-800",
|
||||
"modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed",
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"gpuType": "hygon_k100-ai",
|
||||
"modelId": "Edge0/Edge0-35B-A3B-preview",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4970003,
|
||||
"taskId": 4849007,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 10,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:52.043508+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5_moe"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm-patch-tokenizer"
|
||||
],
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"gpuType": "hygon_k100-ai",
|
||||
"modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4860051,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 11,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:51.297854+00:00",
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:52.043508+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
"model_type:qwen3_5_moe"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
"vllm-patch-tokenizer"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Kunlunxin_p-800",
|
||||
"modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16",
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"gpuType": "hygon_k100-ai",
|
||||
"modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4969637,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 11,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:51.297854+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Kunlunxin_p-800",
|
||||
"modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4970006,
|
||||
"taskId": 4860052,
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
],
|
||||
@@ -327,288 +285,240 @@
|
||||
"unsloth/LFM2-2.6B-Exp-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/unsloth/LFM2-2.6B-Exp-GGUF/resolve/master/config.json (status=404)",
|
||||
"z-lab/Qwen3.8-27B-DFlash2-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/z-lab/Qwen3.8-27B-DFlash2-GGUF/resolve/master/config.json (status=404)"
|
||||
},
|
||||
"architectureModelConfigsComplete": 71,
|
||||
"architectureModelConfigsComplete": 68,
|
||||
"architectureOnly": true,
|
||||
"architecturePolicySkipped": {
|
||||
"frameworkCatalogUnknown": 0,
|
||||
"frameworkContextUnknown": 87,
|
||||
"frameworkContextUnknown": 84,
|
||||
"modelArchitectureUnknown": 134,
|
||||
"noMatchingBlock": 980,
|
||||
"noMatchingBlock": 976,
|
||||
"partiallyBlockedFrameworkSet": 24,
|
||||
"runningMatchedProtected": 0,
|
||||
"submissionContextMismatch": 0,
|
||||
"submissionContextUnknown": 0
|
||||
},
|
||||
"cancelledCount": 11,
|
||||
"cancelledCount": 9,
|
||||
"cancelledTasks": [
|
||||
{
|
||||
"accountIndex": 1,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:51.297854+00:00",
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:52.043508+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
"model_type:qwen3_5_moe"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
"vllm-patch-tokenizer"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Kunlunxin_p-800",
|
||||
"modelId": "EschaLabs/Qwen3.8-27B-Escha-W2",
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"gpuType": "hygon_k100-ai",
|
||||
"modelId": "primitive-ai/Nex-N2.5-mini-FP8",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4969333,
|
||||
"taskId": 4754068,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 2,
|
||||
"accountIndex": 3,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:51.297854+00:00",
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:52.043508+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
"model_type:qwen3_5_moe"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
"vllm-patch-tokenizer"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Kunlunxin_p-800",
|
||||
"modelId": "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo",
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"gpuType": "hygon_k100-ai",
|
||||
"modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4969326,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 2,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:51.297854+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Kunlunxin_p-800",
|
||||
"modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4970000,
|
||||
"taskId": 4969661,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 4,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:51.297854+00:00",
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:52.043508+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
"model_type:qwen3_5_moe"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
"vllm-patch-tokenizer"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Kunlunxin_p-800",
|
||||
"modelId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo",
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"gpuType": "hygon_k100-ai",
|
||||
"modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4969328,
|
||||
"taskId": 4849006,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 5,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:51.297854+00:00",
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:52.043508+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
"model_type:qwen3_5_moe"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
"vllm-patch-tokenizer"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Kunlunxin_p-800",
|
||||
"modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit",
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"gpuType": "hygon_k100-ai",
|
||||
"modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4969043,
|
||||
"taskId": 4923872,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 5,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:52.043508+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5_moe"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm-patch-tokenizer"
|
||||
],
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"gpuType": "hygon_k100-ai",
|
||||
"modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4939007,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 7,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:51.297854+00:00",
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:52.043508+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
"model_type:qwen3_5_moe"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
"vllm-patch-tokenizer"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Kunlunxin_p-800",
|
||||
"modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw",
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"gpuType": "hygon_k100-ai",
|
||||
"modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4969331,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 8,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:51.297854+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Kunlunxin_p-800",
|
||||
"modelId": "ornith-ai/Ornith-1.5-9B-NVFP4",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4969322,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 8,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:51.297854+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Kunlunxin_p-800",
|
||||
"modelId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4969332,
|
||||
"taskId": 4795634,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 10,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:51.297854+00:00",
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:52.043508+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
"model_type:qwen3_5_moe"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
"vllm-patch-tokenizer"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Kunlunxin_p-800",
|
||||
"modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed",
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"gpuType": "hygon_k100-ai",
|
||||
"modelId": "Edge0/Edge0-35B-A3B-preview",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4970003,
|
||||
"taskId": 4849007,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 10,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:52.043508+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5_moe"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm-patch-tokenizer"
|
||||
],
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"gpuType": "hygon_k100-ai",
|
||||
"modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4860051,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 11,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:51.297854+00:00",
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:52.043508+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
"model_type:qwen3_5_moe"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
"vllm-patch-tokenizer"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Kunlunxin_p-800",
|
||||
"modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16",
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"gpuType": "hygon_k100-ai",
|
||||
"modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4969637,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 11,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:51.297854+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Kunlunxin_p-800",
|
||||
"modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4970006,
|
||||
"taskId": 4860052,
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
],
|
||||
"certainOomCount": 0,
|
||||
"certainOomTasks": [],
|
||||
"cleanupCandidateCount": 11,
|
||||
"cleanupCandidateCount": 9,
|
||||
"dryRun": false,
|
||||
"listingErrors": {},
|
||||
"modelAgeErrors": {},
|
||||
@@ -633,7 +543,7 @@
|
||||
],
|
||||
"oldOverflowCount": 0,
|
||||
"oldOverflowTasks": [],
|
||||
"policyCancelledRecorded": 11,
|
||||
"policyCancelledRecorded": 9,
|
||||
"policyNoLongerAppliesCount": 0,
|
||||
"policyNoLongerAppliesTasks": [],
|
||||
"recentModelDays": 7,
|
||||
@@ -646,5 +556,5 @@
|
||||
"repositorySizeUnknown": 0
|
||||
},
|
||||
"stopErrors": [],
|
||||
"uniqueModels": 347
|
||||
"uniqueModels": 344
|
||||
}
|
||||
|
||||
@@ -1,3 +1,6 @@
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-20T18:53:01.472996+00:00", "modelId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T18:51:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4523697", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-20T18:53:01.473044+00:00", "modelId": "fla-hub/rwkv7-191M-world", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T18:49:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079911", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "runtime_memory", "failureAction": "lower_memory_risk_or_reject_combination", "failureCategory": "runtime_memory", "failureClassificationReason": "structured_device_oom", "failureCode": "DEVICE_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu", "framework": "vllm", "lastSyncTime": "2026-09-20T18:53:01.473084+00:00", "modelId": "vllm-ascend/Qwen3-32B-w8a8sc-310-vllm-tp4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T18:47:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079186", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-20T18:36:43.146458+00:00", "modelId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T18:33:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4523880", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-20T17:39:36.352421+00:00", "modelId": "bharatgenai/Param2-17B-A2.4B-Thinking", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T17:25:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4592187", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-20T16:40:51.571551+00:00", "modelId": "KoboldAI/fairseq-dense-13B-Janeway", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T16:37:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079152", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -115,10 +118,12 @@
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.600137+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:09:19.090425+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969392", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.600306+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926484304, "estimatedRequiredGiB": 26.777, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23959625409, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107212656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23959625409}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:09:19.045622+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969391", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.600018+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26090095180, "modelscopeLicense": "apache-2.0", "modelscopeParams": 21416999792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:fp8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26090095180}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:09:18.989339+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969386", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T18:53:01.473025+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663396475, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663396475}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:09:18.549276+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969363", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["zaya"], "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T11:30:54.600365+00:00", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463599, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463599}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:09:18.452113+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969361", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T14:32:15.260751+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16779959304, "estimatedRequiredGiB": 18.777, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16801630203, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8389956608, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16801630203}, "outcome": "success", "status": "success", "submitTime": "2026-09-20T03:09:18.440547+00:00", "targetGpu": "Biren_166m", "taskId": "4969359", "taskType": "text-generation", "verifyResult": 1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T18:18:38.666111+00:00", "modelId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 219850592, "estimatedRequiredGiB": 0.249, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 223236742, "modelscopeLicense": "apache-2.0", "modelscopeParams": 162826560, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 223236742}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:09:11.539809+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969300", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T18:18:38.666090+00:00", "modelId": "LiquidAI/LFM2.5-2.6B", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427456, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412393192, "modelscopeLicense": "other", "modelscopeParams": 2697198592, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5412393192}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:09:11.537727+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969303", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T18:53:01.473075+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37184031394, "estimatedRequiredGiB": 41.579, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 37204398600, "modelscopeLicense": "apache-2.0", "modelscopeParams": 10061358960, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:mixed-precision", "custom_tag:qwen3.6", "custom_tag:agentic-search"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37204398600}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:52.043508+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969075", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedArchitectures": ["Cohere2ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-20T17:09:45.266177+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730845002, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730845002}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:51.937617+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4969071", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T16:44:23.353846+00:00", "modelId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 42709318472, "estimatedRequiredGiB": 47.753, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 42728540075, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553707056, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 42728540075}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:51.842110+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969064", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T17:09:45.266185+00:00", "modelId": "sapientinc/HRM-Text-1B", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2365606568, "estimatedRequiredGiB": 2.651, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 2371660433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1182795264, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:hrm", "custom_tag:hierarchical-reasoning", "custom_tag:prefix-lm", "custom_tag:pre-alignment", "custom_tag:non-chat", "custom_tag:non-instruction-tuned"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2371660433}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:51.693959+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969057", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -132,6 +137,7 @@
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T18:18:38.666148+00:00", "modelId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22210552448, "estimatedRequiredGiB": 24.849, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 22234091413, "modelscopeLicense": "apache-2.0", "modelscopeParams": 17463440388, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:fp8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:speculative-decoding", "custom_tag:blackwell", "custom_tag:a100"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 22234091413}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:51.336010+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969039", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T18:18:38.666126+00:00", "modelId": "naver-hyperclovax/HyperCLOVAX-SEED-Think-32B", "modelProfile": {"architectures": ["HyperCLOVAXVisionV2ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 66626957488, "estimatedRequiredGiB": 74.478, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hyperclovax_vision_v2", "modelscopeFileSize": 66642228907, "modelscopeLicense": "other", "modelscopeParams": 33313410304, "modelscopeTags": ["license:other", "model_type:hyperclovax_vision_v2", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 66642228907}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:51.307162+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969037", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T17:54:13.170257+00:00", "modelId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 36679335352, "estimatedRequiredGiB": 41.028, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 36711610638, "modelscopeLicense": "apache-2.0", "modelscopeParams": 18339618304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:pruning", "custom_tag:width-pruning", "custom_tag:zero-training", "custom_tag:qwen3_5", "custom_tag:gated-deltanet"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36711610638}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:51.297854+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969036", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T18:53:01.473054+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v3-9B", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18483466448, "estimatedRequiredGiB": 20.702, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 18523972484, "modelscopeLicense": "gemma", "modelscopeParams": 9241705984, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18523972484}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:50.898445+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969015", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-19T23:13:47.695492+00:00", "modelId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-19T23:07:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477839", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-19T23:13:47.695526+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-19T23:07:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4458016", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-19T23:04:02.598845+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-19T23:03:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4609086", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -292,9 +298,3 @@
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "unknown", "failureCode": "UNKNOWN", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-15T00:22:04.249539+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T00:17:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4595877", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-15T00:03:42.210358+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T00:03:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4592744", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-15T00:03:42.210382+00:00", "modelId": "RWKV/RWKV7-7.2B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T23:57:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4591876", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-15T00:03:42.210393+00:00", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T23:55:23+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4592637", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-14T23:27:02.946784+00:00", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T23:19:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4332398", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-14T23:17:30.142642+00:00", "modelId": "RWKV/RWKV7-7.2B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T23:09:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4588001", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-14T21:58:01.543573+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T21:57:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4580941", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-14T21:58:01.543590+00:00", "modelId": "OpenOneRec/OneReason-8B-pretrain-competition", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T21:57:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4609082", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-14T21:47:28.713808+00:00", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T21:43:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4593059", "taskType": "text-generation", "verifyResult": -1}
|
||||
|
||||
@@ -1738,6 +1738,72 @@
|
||||
{"batchId": "748c2571b3404f7eacf07d9209eb073f", "completedAt": "2026-09-20T18:47:13.376634+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:39:27.655629+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8fdb400a0dfe4775a7ddfa4fd588864d", "lastModified": "2026-08-24T20:01:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "reason": null, "reconciledAt": "2026-09-20T18:51:33.444278+00:00", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "4985663", "taskType": "text-generation"}
|
||||
{"batchId": "748c2571b3404f7eacf07d9209eb073f", "completedAt": "2026-09-20T18:47:13.376663+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:39:27.656025+00:00", "framework": "vllm-mlu", "intentId": "1c5d70f0fac74c119617484ebf63526b", "lastModified": "2026-08-26T19:43:40+00:00", "modelAddress": "https://modelscope.cn/models/inceptionai/Jais-2-8B-Chat", "reason": null, "reconciledAt": "2026-09-20T18:51:33.444554+00:00", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4985692", "taskType": "text-generation"}
|
||||
{"batchId": "070db734079f4aca9551a5cf6b84acd8", "completedAt": "2026-09-20T18:51:31.954982+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:47:14.182259+00:00", "framework": "vllm-customized", "intentId": "470923c8dd894be8b6a39eded0a3d13b", "lastModified": "2026-09-04T12:06:11+00:00", "modelAddress": "https://modelscope.cn/models/sapientinc/HRM-Text-1B", "reason": null, "reconciledAt": "2026-09-20T18:51:33.442005+00:00", "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4985774", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.632970+00:00", "framework": "vllm_tokenizer_patch", "intentId": "29415d6fcf7b49b6b5b680ff029f57bc", "lastModified": "2026-08-24T19:39:27+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-FP8", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633081+00:00", "framework": "vllm-mlu", "intentId": "53d05c77376e4e39a82e4d4fb2f6fb31", "lastModified": "2026-08-24T19:46:26+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a8", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633137+00:00", "framework": "vllm-mlu", "intentId": "7c3ff29f2362400ea07ddc1d051bdd80", "lastModified": "2026-08-24T20:05:18+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633188+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e170d093182d4b55963ec22fdaec989b", "lastModified": "2026-08-24T19:42:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-FP8", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633230+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e56bbb79d2af49aba071bbc0f132defb", "lastModified": "2026-08-24T19:44:39+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a8", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633269+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4d87448a072f43939da6f1dd9042e10a", "lastModified": "2026-08-24T19:41:12+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633308+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fd269724b144421fbfa386856b5f7d44", "lastModified": "2026-08-24T19:39:57+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633346+00:00", "framework": "vllm_tokenizer_patch", "intentId": "562eb0277eb04deea7243014bf92bc2f", "lastModified": "2026-08-24T19:39:28+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633383+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f46e393f4d834972a6beb8d113afd971", "lastModified": "2026-08-24T19:59:13+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-FP8", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633421+00:00", "framework": "vllm_tokenizer_patch", "intentId": "339b9502c51447ef9ec16d113552671f", "lastModified": "2026-08-24T19:51:52+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633458+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5d14d53c805b4be2adf7af31fd8204d6", "lastModified": "2026-08-24T20:01:57+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w4a16", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633496+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d55960e2d4174e288ef45d4334d7f1e1", "lastModified": "2026-08-24T20:02:01+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-quantized.w8a16", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633533+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d308cad63b6f450ba3f7f80526ee7c1d", "lastModified": "2026-08-24T19:40:10+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-quantized.w8a8", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633585+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4c28895945674ca7b91d54723ff863d5", "lastModified": "2026-08-24T20:06:34+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633635+00:00", "framework": "vllm", "intentId": "304721cce5eb4813a7078592dc16a4f6", "lastModified": "2026-09-10T05:31:36+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-NVFP4", "repoId": "primitive-ai/Nex-N2.5-mini-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633702+00:00", "framework": "vllm", "intentId": "be04f7a784f84f20bb7062cbca8724ba", "lastModified": "2026-08-31T14:36:00+00:00", "modelAddress": "https://modelscope.cn/models/ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "repoId": "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633761+00:00", "framework": "vllm", "intentId": "8a86c35a8bed4a26949ca18c523b18c8", "lastModified": "2026-08-31T23:02:41+00:00", "modelAddress": "https://modelscope.cn/models/ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "repoId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633818+00:00", "framework": "vllm", "intentId": "3347a771c9fe4d06941f2cc163197ab7", "lastModified": "2026-09-09T06:31:08+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633875+00:00", "framework": "vllm", "intentId": "6c9369f65d524741b094df4a57675243", "lastModified": "2026-09-02T05:56:49+00:00", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "repoId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633931+00:00", "framework": "vllm", "intentId": "4bb5bb82553f4bb9afa64a2cf73be5d0", "lastModified": "2026-09-08T15:45:26+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.633989+00:00", "framework": "vllm", "intentId": "a39c2113e7374b3a92d8ab5419528c81", "lastModified": "2026-08-26T20:08:51+00:00", "modelAddress": "https://modelscope.cn/models/VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "repoId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634091+00:00", "framework": "vllm", "intentId": "4fa5f82106984218a9f29d98b9dcc809", "lastModified": "2026-09-03T07:00:50+00:00", "modelAddress": "https://modelscope.cn/models/EschaLabs/Qwen3.8-27B-Escha-W2", "repoId": "EschaLabs/Qwen3.8-27B-Escha-W2", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634148+00:00", "framework": "vllm", "intentId": "5dad35547b464dabb1ba3c3cc232e47e", "lastModified": "2026-08-24T20:29:58+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634204+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c440ef54fa3043d2b0de67ee3d143782", "lastModified": "2026-08-24T20:20:16+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-FP8", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634248+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1fa64f9af840479d91e82bc23d00716d", "lastModified": "2026-08-24T20:26:53+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634292+00:00", "framework": "vllm_fix_tokenizer", "intentId": "75941df9c92c4eba964806c3694a543c", "lastModified": "2026-08-26T12:23:38+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634335+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ed9e23f23d964907af0b614676fb193f", "lastModified": "2026-09-09T06:27:24+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634379+00:00", "framework": "vllm_fix_tokenizer", "intentId": "03d7a74f48d248e4a30895ce1b5c3cd6", "lastModified": "2026-08-26T14:51:55+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-GPTQ", "repoId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634422+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8d50b356d2b74c93bbdafa4fadb2f942", "lastModified": "2026-08-28T05:30:04+00:00", "modelAddress": "https://modelscope.cn/models/whcl412/mlx-LycheeAI-coder-1.7b", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634465+00:00", "framework": "vllm-patch-tokenizer", "intentId": "2a1225e1abe64a518c9816fcf65a158d", "lastModified": "2026-08-24T20:04:01+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634508+00:00", "framework": "vllm-patch-tokenizer", "intentId": "59ca23712857479fba56ff3a8d7e96af", "lastModified": "2026-08-24T19:53:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634551+00:00", "framework": "vllm-patch-tokenizer", "intentId": "5a77ae1f99374ee58e36d8947d894167", "lastModified": "2026-08-24T20:09:59+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-2-7b-chat-quantized.w8a8", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634593+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a3173fc554304e6ea1497dac76ac3cf9", "lastModified": "2026-08-24T20:22:00+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a16", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634636+00:00", "framework": "vllm-patch-tokenizer", "intentId": "bfb928b9cc52431ab442c61ee4e545c0", "lastModified": "2026-08-24T20:10:58+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634685+00:00", "framework": "vllm-patch-tokenizer", "intentId": "f6e1affc710f4602a1e6f63a0fdedf0f", "lastModified": "2026-08-24T20:22:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634727+00:00", "framework": "vllm-patch-tokenizer", "intentId": "c6a03b817144486f95b02ee507817756", "lastModified": "2026-08-24T20:14:53+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w4a16", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634769+00:00", "framework": "vllm-patch-tokenizer", "intentId": "52fa13a2386a473f83d97d6d5c379e07", "lastModified": "2026-08-24T19:39:21+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w8a16", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634811+00:00", "framework": "vllm-patch-tokenizer", "intentId": "99ed4c0273284d67979c3a391cdecd5b", "lastModified": "2026-08-24T19:48:09+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634853+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a7ee602476d8428da3fa564f7a8e1724", "lastModified": "2026-08-24T20:21:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634896+00:00", "framework": "vllm-patch-tokenizer", "intentId": "41f7c65309204d08bbfe08340e24e2c5", "lastModified": "2026-08-24T19:53:24+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "repoId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634939+00:00", "framework": "vllm-patch-tokenizer", "intentId": "abd721f8f3c64bd7ab44f27c7b0c7ee6", "lastModified": "2026-08-24T20:36:33+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.634982+00:00", "framework": "vllm-patch-tokenizer", "intentId": "889c0d2c369041d9b6d6d0aded14b595", "lastModified": "2026-08-24T20:09:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-3B-Instruct-FP8", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635024+00:00", "framework": "vllm-patch-tokenizer", "intentId": "63190001dd954e5e9032f752b0e7cbb6", "lastModified": "2026-08-24T20:17:00+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635066+00:00", "framework": "vllm-patch-tokenizer", "intentId": "9fb39de03c9244a9865d8adddc396ac0", "lastModified": "2026-08-24T20:08:44+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635108+00:00", "framework": "vllm-patch-tokenizer", "intentId": "075e6d2eba034de2ae341bcbb8ab2db0", "lastModified": "2026-08-24T20:20:16+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-FP8", "repoId": "RedHatAI/starcoder2-15b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635151+00:00", "framework": "vllm-patch-tokenizer", "intentId": "4592ed487edf42beaba3cd5861adce3a", "lastModified": "2026-08-24T20:18:47+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-27b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635193+00:00", "framework": "vllm-patch-tokenizer", "intentId": "566758a6357f4f6bb144d89c39c444fb", "lastModified": "2026-08-24T22:06:31+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-FP8", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635236+00:00", "framework": "vllm-patch-tokenizer", "intentId": "e1e13bfe2def4fb28ecac0872a94ea9a", "lastModified": "2026-08-26T16:45:23+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635278+00:00", "framework": "vllm", "intentId": "17a87c01dc3c4d808bbdc9f3642e9f88", "lastModified": "2026-08-24T19:57:49+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635327+00:00", "framework": "vllm", "intentId": "3692fcabaea3455f88031bc99bcda614", "lastModified": "2026-08-24T19:54:53+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-3B-Instruct-FP8", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635375+00:00", "framework": "vllm", "intentId": "8053a91bf7a147aeb15d80f54e16f458", "lastModified": "2026-08-24T19:53:24+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w4a16", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635423+00:00", "framework": "vllm", "intentId": "529d4a0a4415467393914fc525620382", "lastModified": "2026-08-24T20:02:14+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635471+00:00", "framework": "vllm", "intentId": "96a2b16b1b3948629fb955abc9f4a239", "lastModified": "2026-09-11T15:31:18+00:00", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "repoId": "CohereLabs/tiny-aya-en-thinker", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635518+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4eed6acd64d841bf9a0554b939cecd34", "lastModified": "2026-08-26T17:20:09+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635562+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f83def65cc1a4fd9b11a7a76fbf6616f", "lastModified": "2026-08-26T20:08:57+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635602+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3281c8ff3b274012b98e00585fa82d25", "lastModified": "2026-08-24T20:36:29+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635642+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6567432b556a4a79bab994a74f6cdf9f", "lastModified": "2026-08-24T20:38:11+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635686+00:00", "framework": "vllm_tokenizer_patch", "intentId": "63929a1cbfd6427ca335ffdf0965b243", "lastModified": "2026-08-26T18:16:42+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-Research", "repoId": "aisingapore/SEA-LION-v1-7B-IT-Research", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635726+00:00", "framework": "vllm-customized", "intentId": "5264b955e5a344d0b64b5f18cc1e0c02", "lastModified": "2026-09-09T12:19:20+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/BitCPM-CANN-8B", "repoId": "OpenBMB/BitCPM-CANN-8B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635786+00:00", "framework": "vllm-customized", "intentId": "52b81e6028c9474aa912a908dd823761", "lastModified": "2026-08-24T22:55:11+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/AquilaMed-RL", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635844+00:00", "framework": "vllm-customized", "intentId": "15086f61087b4b3cab0f3b5ec4da46cc", "lastModified": "2026-08-24T20:26:05+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "repoId": "neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635902+00:00", "framework": "vllm-customized", "intentId": "a02ceaa273bf47209596ad95bf273320", "lastModified": "2026-09-03T13:37:32+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B", "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.635960+00:00", "framework": "vllm-customized", "intentId": "0573f4bda9c846b786872eb57a10cf62", "lastModified": "2026-08-24T20:15:22+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "repoId": "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.636018+00:00", "framework": "vllm-customized", "intentId": "3c2871c6a7d94965861f0e37d7014653", "lastModified": "2026-08-24T20:22:22+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.636075+00:00", "framework": "vllm-customized", "intentId": "56028211ea4f4948957f28560878403f", "lastModified": "2026-09-08T13:43:47+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
|
||||
{"batchId": "fab8fc98780349e99e8b3476b735dd02", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:54:42.636132+00:00", "framework": "vllm-customized", "intentId": "34ac1cf1319a4fa08b40890c707b3370", "lastModified": "2026-08-29T01:07:23+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "repoId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
|
||||
{"batchId": "070db734079f4aca9551a5cf6b84acd8", "completedAt": "2026-09-20T18:51:31.955066+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:47:14.183624+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1724a619ac5248c590d484cf71f3b79f", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
|
||||
{"batchId": "070db734079f4aca9551a5cf6b84acd8", "completedAt": "2026-09-20T18:51:31.955063+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:47:14.183569+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1fcbdc0dc1f24b90b55e899f6560a152", "repoId": "mlx-community/Spark-X2.5-4B-OptiQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
|
||||
{"batchId": "070db734079f4aca9551a5cf6b84acd8", "completedAt": "2026-09-20T18:51:31.955060+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T18:47:14.183515+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a6a4fe8617024da4ab3f3de4da172270", "repoId": "aisingapore/Llama-SEA-LION-v3-8B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
|
||||
|
||||
@@ -1,24 +1,24 @@
|
||||
{
|
||||
"agentVersion": "2026.09.20.2",
|
||||
"checksums": {
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "392c605b0cb2d3ad04b975a6b3dde0a3ce7498e1ccb39dfce89a67617d81b711",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "b77c5319e7908364742025df13d68f9c2f15b2fbce1c4bd9a51950fd3cbca9b9",
|
||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||
".modelhub_state/market_intelligence.json": "84ca27268f851184e9fde5a1fb10bbf89e9f5b4e4af810c2979212f7652d4b38",
|
||||
".modelhub_state/official_capabilities.json": "531f6eca145572c969d194526bbff1bc239dfced49591163b302cddb5b9d56ac",
|
||||
".modelhub_state/outcome_checkpoint.json": "1699eac230b5d2d2209c845f7c41efb09600e3f74064f12149fa004f59b865af",
|
||||
".modelhub_state/queue_cleanup_latest.json": "8adf50d70007001b58523d77353a08b9caccc5d440d98c6b60248a1c3b9811b4",
|
||||
".modelhub_state/recent_outcomes.jsonl": "06a006d970484816b79d77d22319be24df9f9cc6465e6b70be4375dbd2299ae0",
|
||||
".modelhub_state/market_intelligence.json": "38937ba25161c0380b7f8d30166616f329810cc0cb93f9b358940583e4d4f255",
|
||||
".modelhub_state/official_capabilities.json": "b6048ad0c2ffd56736ad157693e8428ea9279610fc69183350697eeae4287406",
|
||||
".modelhub_state/outcome_checkpoint.json": "d48f0d31bc877abba8120fcdaeef2a73bc475c65f88b2d69124ce978d7aef680",
|
||||
".modelhub_state/queue_cleanup_latest.json": "51060760318808c95c5f937aac9389cef4379d95a33f6213764b0f798b1c6bb9",
|
||||
".modelhub_state/recent_outcomes.jsonl": "15e6bd7829e8e77d7c46a9e2035cd3a77ca652112c645fe83c727c723083bd64",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "4c461c92d603ecbd77094fd4fa2b870a759f7eb06a9c7151b2f230c9dc442216",
|
||||
".modelhub_state/recovery_intents.jsonl": "d919b3588c80cf00bb6dc2830badd6325ff8e1d7597af633588bc80eb7b4f1c3",
|
||||
".modelhub_state/recovery_intents.jsonl": "ec54399b29c319c8ea4727fd6409300e23fcb3f235dc71be461e28d41995a8a6",
|
||||
".modelhub_state/routing_intelligence.json": "a124ea5f4e4a166a71780eb04d0b25316cb234982b1e4094a310afd0533d79af",
|
||||
".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7",
|
||||
".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23",
|
||||
"ledger/submissions.jsonl": "33d632e4287a24b09eff3aac40157874c8547810b1203853ebc9c5d9e112c3aa",
|
||||
"outcomes/submissions.jsonl": "695793bb168595070f4f3e7ed30b273a3442a1d5d597a238a72e9b4147feb8a3"
|
||||
"outcomes/submissions.jsonl": "4111dea6a0564f5ff0ed20fbfd4372c166de13ff036fc6fea184ed87d2c92f9c"
|
||||
},
|
||||
"generation": 10809,
|
||||
"phase": "cycle",
|
||||
"generation": 10810,
|
||||
"phase": "intent",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-20T18:52:00.489197+00:00",
|
||||
"updatedAt": "2026-09-20T18:54:42.831310+00:00",
|
||||
"writerId": "fc715c06e24c4db2ae3e425e435db996"
|
||||
}
|
||||
|
||||
@@ -144,7 +144,6 @@
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-10T13:55:40.785159+00:00", "modelId": "bartowski/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "1764a9124cd000c7904ba9cee10ecdf5f9bfd4e65fc6896e0120a683f5e606e3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1516997856, "estimatedRequiredGiB": 40.615, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36341551917}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:54:18.783901+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4754025", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T14:03:50.607039+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926484304, "estimatedRequiredGiB": 26.777, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107212656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23959625409}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:55:59.442486+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4754066", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T14:03:50.607077+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 21416999792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:fp8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26090095180}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:55:59.435840+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4754067", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-10T14:03:50.607061+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 38136526544, "estimatedRequiredGiB": 42.65, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:fp8", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 38162746086}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:55:59.437900+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4754068", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T14:03:50.607069+00:00", "modelId": "BAAI/AREX-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9078620368, "estimatedRequiredGiB": 10.18, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9109259594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4539265536, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:deep-research", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:qwen3.5", "custom_tag:dense"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9109259594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:03:37.655467+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4754205", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-10T14:13:15.207776+00:00", "modelId": "bartowski/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "37bac6ce21d60134ebaca4c6569bab1151fd62af1ad962effbf472bc8bdbafbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1516997856, "estimatedRequiredGiB": 40.615, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 36341551917, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36341551917}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:11:11.806743+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4754342", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-10T14:29:51.626225+00:00", "modelId": "bartowski/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "9ee85a9702ae695242c8b5436b1b856292d4a16c2f839d36bf93fbe98fb66d4e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1516997856, "estimatedRequiredGiB": 40.615, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 36341551917, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36341551917}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:28:56.145522+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4754660", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -195,7 +194,6 @@
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-12T13:02:08.318710+00:00", "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730839322, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T04:52:57.116897+00:00", "targetGpu": "Biren_166m", "taskId": "4794241", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-12T13:02:08.318700+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12999919368, "estimatedRequiredGiB": 14.555, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 13023155398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3544073216, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:imatrix", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13023155398}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T04:52:57.114996+00:00", "targetGpu": "Biren_166m", "taskId": "4794242", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-12T14:23:18.821537+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37721402856, "estimatedRequiredGiB": 42.187, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 37748367893, "modelscopeLicense": "mit", "modelscopeParams": 10195701616, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37748367893}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T06:19:56.330927+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4795478", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-12T14:41:33.434314+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37721402856, "estimatedRequiredGiB": 42.187, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 37748367893, "modelscopeLicense": "mit", "modelscopeParams": 10195701616, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37748367893}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T06:36:56.396629+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4795634", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-12T18:59:53.316548+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37721402856, "estimatedRequiredGiB": 42.187, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 37748367893, "modelscopeLicense": "mit", "modelscopeParams": 10195701616, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-09T14:00:25.508497+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 37748367893}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T10:58:56.807180+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4800525", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-12T18:59:53.316560+00:00", "modelId": "unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 65827374264, "estimatedRequiredGiB": 73.588, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 65845719365, "modelscopeLicense": "other", "modelscopeParams": 32913266240, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 65845719365}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T10:58:56.798553+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4800526", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-12T22:16:38.428761+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37721402856, "estimatedRequiredGiB": 42.187, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 37748367893, "modelscopeLicense": "mit", "modelscopeParams": 10195701616, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37748367893}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T14:09:52.635448+00:00", "targetGpu": "Biren_166m", "taskId": "4803464", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -236,8 +234,6 @@
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-14T18:50:27.851852+00:00", "modelId": "aucaCQS/Spark-X2.5-4B-Coder-Flash", "modelProfile": {"architectures": [], "configFingerprint": "6270b79db6f53655ba1dc1b7e093937b145df2e6fa5dc1d91f6c309d1008d815", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021120, "estimatedRequiredGiB": 37.948, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 32173498806, "modelscopeLicense": null, "modelscopeParams": 4112079360, "modelscopeTags": ["library:gguf", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 33955496536}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T10:42:38.360078+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4847818", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-14T19:09:56.106587+00:00", "modelId": "aucaCQS/Spark-X2.5-4B-Coder-Flash", "modelProfile": {"architectures": [], "configFingerprint": "f0079c5722ce37ff9d929e5e96de8925a4670b711936f17faab5f7565f2ecb43", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021120, "estimatedRequiredGiB": 37.948, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 32173498806, "modelscopeLicense": null, "modelscopeParams": 4112079360, "modelscopeTags": ["library:gguf", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 33955496536}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T10:59:43.480777+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4847964", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-14T20:39:18.216494+00:00", "modelId": "aucaCQS/Spark-X2.5-4B-Coder-Flash", "modelProfile": {"architectures": [], "configFingerprint": "327b4fcce82afa7c692364047b27c53d2b6ae7a0f2522806938c3c935ae9a735", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021120, "estimatedRequiredGiB": 37.948, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 33955496529, "modelscopeLicense": null, "modelscopeParams": 4112079360, "modelscopeTags": ["library:gguf", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 33955496529}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T12:34:59.173731+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4849005", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-14T20:39:18.216500+00:00", "modelId": "Edge0/Edge0-35B-A3B-preview", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19689863445, "estimatedRequiredGiB": 22.059, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 19738195355, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5419330688, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19738195355}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T12:34:59.176520+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4849007", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-14T20:39:18.216485+00:00", "modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269528840, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13269528840}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T12:34:59.178065+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4849006", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-14T21:58:01.543536+00:00", "modelId": "yujianboisme/qwen2.5-1.5b-darkhorse-code-fine-tuning", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3087467712, "estimatedRequiredGiB": 3.468, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 802490000, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1543714304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:text-generation", "custom_tag:qwen2.5", "custom_tag:lora", "custom_tag:json", "custom_tag:instruction-following", "custom_tag:chinese", "custom_tag:command-translation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3103395696}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T13:50:28.944104+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4849951", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-14T22:08:38.089531+00:00", "modelId": "yujianboisme/qwen2.5-1.5b-darkhorse-code-fine-tuning", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3087467712, "estimatedRequiredGiB": 3.468, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 802490000, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1543714304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:text-generation", "custom_tag:qwen2.5", "custom_tag:lora", "custom_tag:json", "custom_tag:instruction-following", "custom_tag:chinese", "custom_tag:command-translation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3103395696}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T14:07:56.405960+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4850193", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-14T22:30:56.809240+00:00", "modelId": "yujianboisme/qwen2.5-1.5b-darkhorse-code-fine-tuning", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3087467712, "estimatedRequiredGiB": 3.468, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 3103395696, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1543714304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:text-generation", "custom_tag:qwen2.5", "custom_tag:lora", "custom_tag:json", "custom_tag:instruction-following", "custom_tag:chinese", "custom_tag:command-translation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3103395696}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T14:28:45.912561+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4850731", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -262,8 +258,6 @@
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-15T05:54:37.536172+00:00", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269529266, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13269529926}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T21:47:17.027666+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4857813", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-15T06:16:21.605496+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20063537850, "estimatedRequiredGiB": 22.446, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20083973356, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5529413488, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20083974016}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T22:08:21.049320+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4858026", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-15T06:16:21.605550+00:00", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269529266, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13269529926}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T22:08:21.042712+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4858025", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-15T07:00:32.211817+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20063537850, "estimatedRequiredGiB": 22.446, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20083974016, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5529413488, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20083974016}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T22:58:26.642767+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4860051", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-15T07:00:32.211840+00:00", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269529926, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13269529926}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T22:58:26.648426+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4860052", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-15T07:00:32.211851+00:00", "modelId": "hcnote/SparkMuse-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192576, "estimatedRequiredGiB": 9.203, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8234364261, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:long-context", "custom_tag:1M-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8234364261}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T22:58:26.649925+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4860053", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-15T11:47:43.303103+00:00", "modelId": "hcnote/SparkMuse-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192576, "estimatedRequiredGiB": 9.203, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8234364261, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:long-context", "custom_tag:1M-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8234364261}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-15T03:41:36.840604+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4865836", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-15T11:47:43.303134+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20063537850, "estimatedRequiredGiB": 22.446, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20083974016, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5529413488, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20083974016}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-15T03:41:36.846485+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4865835", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -367,7 +361,6 @@
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-18T05:46:07.695608+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736538977, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13756989526, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13756989526}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T21:45:54.233698+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4923309", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-18T06:05:49.190180+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736538977, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13756989526, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13756989526}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T22:03:22.715585+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4923523", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-18T06:24:52.891825+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736538977, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13756989526, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13756989526}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T22:21:10.450004+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4923702", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-18T06:43:44.292219+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736538977, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13756989526, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13756989526}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T22:38:21.983442+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4923872", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-18T07:01:53.813894+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736538977, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13756989526, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13756989526}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T22:55:35.549905+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4924043", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-18T07:20:15.618254+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736538977, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13756989526, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-15T22:59:41.110897+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 13756989526}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T23:13:41.953804+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4924273", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-18T07:37:57.680700+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736538977, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13756989526, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13756989526}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T23:32:01.618376+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4924477", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -402,7 +395,6 @@
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-19T02:36:05.598906+00:00", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15155811051, "estimatedRequiredGiB": 16.961, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 15176196372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4210722304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:reasoning", "custom_tag:opus-distill", "custom_tag:whittle", "custom_tag:expert-pruning", "custom_tag:moe", "custom_tag:router-healing", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15176196372}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T18:34:31.787488+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4938618", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-19T02:44:40.297028+00:00", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15155811051, "estimatedRequiredGiB": 16.961, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 15176196372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4210722304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:reasoning", "custom_tag:opus-distill", "custom_tag:whittle", "custom_tag:expert-pruning", "custom_tag:moe", "custom_tag:router-healing", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15176196372}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T18:41:55.617980+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4938690", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-19T03:01:51.490259+00:00", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15155811051, "estimatedRequiredGiB": 16.961, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 15176196372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4210722304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:reasoning", "custom_tag:opus-distill", "custom_tag:whittle", "custom_tag:expert-pruning", "custom_tag:moe", "custom_tag:router-healing", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15176196372}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T18:58:28.435554+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4938823", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-19T03:18:50.593299+00:00", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15155811051, "estimatedRequiredGiB": 16.961, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 15176196372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4210722304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:reasoning", "custom_tag:opus-distill", "custom_tag:whittle", "custom_tag:expert-pruning", "custom_tag:moe", "custom_tag:router-healing", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15176196372}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T19:15:30.844293+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4939007", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-19T03:45:21.131949+00:00", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15155811051, "estimatedRequiredGiB": 16.961, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 15176196372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4210722304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:reasoning", "custom_tag:opus-distill", "custom_tag:whittle", "custom_tag:expert-pruning", "custom_tag:moe", "custom_tag:router-healing", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15176196372}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T19:38:31.546614+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4939248", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-19T08:29:40.588024+00:00", "modelId": "soyaakinohara/Spark-X2.5-4B-Heretic-jp-gguf", "modelProfile": {"architectures": [], "configFingerprint": "6f6eecfdce8cb92ba7646b68356f539b9e3b22165c56b20ad43debc6f5797b02", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021184, "estimatedRequiredGiB": 24.098, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 21562254019, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark2_5", "custom_tag:uncensored", "custom_tag:refusal-removed", "custom_tag:quantized", "custom_tag:bf16", "custom_tag:q8_0", "custom_tag:q6_k", "custom_tag:q5_k_m", "custom_tag:q4_k_m", "custom_tag:tool-calling", "custom_tag:japanese", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21562254019}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T00:19:16.727802+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4942012", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-19T08:40:17.761417+00:00", "modelId": "soyaakinohara/Spark-X2.5-4B-Heretic-jp-gguf", "modelProfile": {"architectures": [], "configFingerprint": "27037ea4923276909ffec48c4aaf432c445fc1dc3338331f7fc62f1a8b8c7449", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021184, "estimatedRequiredGiB": 24.098, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 21562254019, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark2_5", "custom_tag:uncensored", "custom_tag:refusal-removed", "custom_tag:quantized", "custom_tag:bf16", "custom_tag:q8_0", "custom_tag:q6_k", "custom_tag:q5_k_m", "custom_tag:q4_k_m", "custom_tag:tool-calling", "custom_tag:japanese", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21562254019}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T00:38:36.958172+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4942203", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -459,7 +451,6 @@
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647749+00:00", "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 7.28, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 6513869659, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1113293776, "modelscopeTags": ["license:Apache License 2.0", "model_type:sophia_hybrid", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6513869659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:50.893989+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969012", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647635+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293473597, "estimatedRequiredGiB": 18.233, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16314185171, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:chat", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16314185171}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:50.937176+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969016", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647793+00:00", "modelId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "modelProfile": {"architectures": ["Mistral3ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17367755740, "estimatedRequiredGiB": 19.429, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral3", "modelscopeFileSize": 17385072379, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4929899520, "modelscopeTags": ["license:apache-2.0", "model_type:mistral3", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:mistral", "custom_tag:mistral3", "custom_tag:devstral"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17385072379}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:50.895856+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969011", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "aisingapore/Gemma-SEA-LION-v3-9B", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18483466448, "estimatedRequiredGiB": 20.702, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 18523972484, "modelscopeLicense": "gemma", "modelscopeParams": 9241705984, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18523972484}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T02:52:50.898445+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969015", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647563+00:00", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8674988799, "estimatedRequiredGiB": 9.718, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8695119291, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2415484144, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:qwen3-5", "custom_tag:9b", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8695119291}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:50.888605+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969013", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647513+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5469228368, "estimatedRequiredGiB": 6.118, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 5473985594, "modelscopeLicense": "mit", "modelscopeParams": 1922048000, "modelscopeTags": ["license:mit", "model_type:mpt", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5473985594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:50.996984+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969020", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647697+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT-Research", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361968, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008118474, "modelscopeLicense": "cc-by-nc-sa-4.0", "modelscopeParams": 7501651968, "modelscopeTags": ["license:cc-by-nc-sa-4.0", "model_type:mpt", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008118474}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.036416+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969019", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -506,7 +497,6 @@
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:00:25.647868+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Base", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2340697936, "estimatedRequiredGiB": 2.621, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 2345547190, "modelscopeLicense": "other", "modelscopeParams": 1170340608, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2345547190}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.956000+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969072", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:00:25.647532+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955963132, "modelscopeLicense": "other", "modelscopeParams": 256113408, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955963132}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:52.136770+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969080", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:00:25.647396+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809686744, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809686744}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:52.134762+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969081", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37184031394, "estimatedRequiredGiB": 41.579, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 37204398600, "modelscopeLicense": "apache-2.0", "modelscopeParams": 10061358960, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:mixed-precision", "custom_tag:qwen3.6", "custom_tag:agentic-search"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37204398600}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T02:52:52.043508+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969075", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:00:25.647657+00:00", "modelId": "aisingapore/Llama-SEA-LION-v2-8B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16060556376, "estimatedRequiredGiB": 17.961, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 16071447395, "modelscopeLicense": "llama3", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16071447395}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:52.096766+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969079", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:00:25.647811+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8842796317, "modelscopeLicense": "mit", "modelscopeParams": 6728625904, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 8842796317}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:52.078583+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969077", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:00:25.647611+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192408, "estimatedRequiredGiB": 9.209, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8239718268, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8239718268}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:52.074544+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969076", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -577,7 +567,6 @@
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:10:38.766339+00:00", "modelId": "sapientinc/HRM-Text-1B", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2365606568, "estimatedRequiredGiB": 2.651, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 2371660433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1182795264, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:hrm", "custom_tag:hierarchical-reasoning", "custom_tag:prefix-lm", "custom_tag:pre-alignment", "custom_tag:non-chat", "custom_tag:non-instruction-tuned"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2371660433}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:18.447188+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969356", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:10:38.766290+00:00", "modelId": "BAAI/RoboBrain2.5-8B-MT", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545918174, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8767123696, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_vl", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17545918174}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:18.449082+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969358", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 34327989512, "estimatedRequiredGiB": 38.385, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 34346039951, "modelscopeLicense": "mit", "modelscopeParams": 32762123264, "modelscopeTags": ["license:mit", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 34346039951}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.543315+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969362", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663396475, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663396475}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.549276+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969363", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:10:38.766033+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:18.555119+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969364", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:10:38.766089+00:00", "modelId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 42709318472, "estimatedRequiredGiB": 47.753, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 42728540075, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553707056, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 42728540075}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:18.638557+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969367", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:10:38.766143+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2340697867, "estimatedRequiredGiB": 2.622, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 2345693224, "modelscopeLicense": "other", "modelscopeParams": 1170340608, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2345693224}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:18.636450+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969365", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -654,7 +643,6 @@
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:30:54.599857+00:00", "modelId": "sbintuitions/sarashina2.2-3b-instruct-v0.1", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6711252896, "estimatedRequiredGiB": 7.503, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 6713123803, "modelscopeLicense": "mit", "modelscopeParams": 3355609600, "modelscopeTags": ["license:mit", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6713123803}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:32.435869+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969657", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:30:54.600275+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248516007, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248516007}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:32.565869+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969664", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:30:54.600169+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2340697867, "estimatedRequiredGiB": 2.621, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 2345554722, "modelscopeLicense": "other", "modelscopeParams": 1170340608, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2345554722}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:32.509994+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969659", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:30:54.599802+00:00", "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21930054875, "estimatedRequiredGiB": 24.532, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 21950415614, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6024588416, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21950415614}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:32.537247+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969661", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:30:54.600405+00:00", "modelId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21855018733, "estimatedRequiredGiB": 24.461, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 21887495988, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6144703054, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21887495988}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:32.538500+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969662", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:30:54.599850+00:00", "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23524076260, "estimatedRequiredGiB": 26.327, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 23556606333, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6649116524, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 23556606333}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:32.639035+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969671", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:30:54.600100+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361928, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008164431, "modelscopeLicense": "mit", "modelscopeParams": 7501651968, "modelscopeTags": ["license:mit", "model_type:mpt", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008164431}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:32.578530+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969666", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -962,11 +950,11 @@
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T18:18:38.666134+00:00", "modelId": "naver-hyperclovax/HyperCLOVAX-SEED-Think-32B", "modelProfile": {"architectures": ["HyperCLOVAXVisionV2ForConditionalGeneration"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 66626957488, "estimatedRequiredGiB": 74.478, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hyperclovax_vision_v2", "modelscopeFileSize": 66642228907, "modelscopeLicense": "other", "modelscopeParams": 33313410304, "modelscopeTags": ["license:other", "model_type:hyperclovax_vision_v2", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 66642228907}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T10:08:01.717933+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4976968", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T18:29:26.057245+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "ecd31d4ed4e0e92b9deabe3de0f18c75dc252004ba68826e4cfd561549549074", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2014810120, "estimatedRequiredGiB": 2.256, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2018195521, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1812039680, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2018195521}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T10:27:44.086595+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4977206", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "transformers", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3430847031, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3430847031}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T10:32:04.275294+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4977311", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093261938, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093261938}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T10:49:41.600448+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4977489", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/starcoder2-7b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7855165704, "estimatedRequiredGiB": 8.783, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7858540940, "modelscopeLicense": "other", "modelscopeParams": 7400416256, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7858540940}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T10:49:41.611337+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4977491", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 7985124714, "modelscopeLicense": "llama2", "modelscopeParams": 10159209984, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7985124714}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T10:49:41.634018+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4977490", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7003604832, "estimatedRequiredGiB": 7.829, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7005626643, "modelscopeLicense": "llama2", "modelscopeParams": 6738415616, "modelscopeTags": ["license:llama2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7005626643}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T10:50:01.755721+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4977518", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2014789064, "estimatedRequiredGiB": 2.255, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2018175215, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1812039680, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2018175215}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T10:51:35.807777+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4977519", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T18:53:01.473068+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093261938, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093261938}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T10:49:41.600448+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4977489", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T18:53:01.473034+00:00", "modelId": "RedHatAI/starcoder2-7b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7855165704, "estimatedRequiredGiB": 8.783, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7858540940, "modelscopeLicense": "other", "modelscopeParams": 7400416256, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7858540940}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T10:49:41.611337+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4977491", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T18:53:01.473061+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 7985124714, "modelscopeLicense": "llama2", "modelscopeParams": 10159209984, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7985124714}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T10:49:41.634018+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4977490", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T18:53:01.473015+00:00", "modelId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7003604832, "estimatedRequiredGiB": 7.829, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7005626643, "modelscopeLicense": "llama2", "modelscopeParams": 6738415616, "modelscopeTags": ["license:llama2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7005626643}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T10:50:01.755721+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4977518", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T18:53:01.472942+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2014789064, "estimatedRequiredGiB": 2.255, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2018175215, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1812039680, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2018175215}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T10:51:35.807777+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4977519", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612744, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788612744}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T11:19:51.535102+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4977812", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14293356304, "estimatedRequiredGiB": 15.977, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14295851911, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14295851911}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T11:19:51.641136+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4977829", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 7985124576, "modelscopeLicense": "llama2", "modelscopeParams": 10159209984, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7985124576}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T11:20:03.373586+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4977833", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user