state: generation 11594 (intent)
This commit is contained in:
@@ -2751,7 +2751,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-21T17:41:29.227970+00:00",
|
||||
"generatedAt": "2026-09-21T18:00:40.567909+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 138,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -434,7 +434,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-21T17:59:11.671356+00:00",
|
||||
"generatedAt": "2026-09-21T18:00:51.251296+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-21T17:41:29.155215+00:00",
|
||||
"lastSyncTime": "2026-09-21T17:41:26.757156+00:00",
|
||||
"generatedAt": "2026-09-21T18:00:40.490817+00:00",
|
||||
"lastSyncTime": "2026-09-21T18:00:38.063699+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -3055,18 +3055,18 @@
|
||||
"unresolvedFailureCount": 17
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
|
||||
"attributableFailureCount": 23,
|
||||
"attributableFailureCount": 24,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 23,
|
||||
"decisionTotal": 24,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 38,
|
||||
"framework_architecture_unsupported": 22,
|
||||
"ambiguous_runtime": 39,
|
||||
"framework_architecture_unsupported": 23,
|
||||
"platform_infrastructure": 1,
|
||||
"repository_structure": 1,
|
||||
"参数/模板问题": 6
|
||||
},
|
||||
"failureCount": 68,
|
||||
"failureCount": 70,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"pendingCount": 0,
|
||||
@@ -3076,24 +3076,24 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 68,
|
||||
"unresolvedFailureCount": 44
|
||||
"total": 70,
|
||||
"unresolvedFailureCount": 45
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation": {
|
||||
"attributableFailureCount": 201,
|
||||
"attributableFailureCount": 203,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 201,
|
||||
"decisionTotal": 203,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 105,
|
||||
"context_length": 1,
|
||||
"framework_architecture_unsupported": 154,
|
||||
"memory_capacity": 9,
|
||||
"framework_architecture_unsupported": 155,
|
||||
"memory_capacity": 10,
|
||||
"platform_infrastructure": 1,
|
||||
"repository_structure": 27,
|
||||
"tokenizer_compatibility": 10
|
||||
},
|
||||
"failureCount": 307,
|
||||
"failureCount": 309,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -3103,7 +3103,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 307,
|
||||
"total": 309,
|
||||
"unresolvedFailureCount": 105
|
||||
},
|
||||
"Biren_166m|unknown|feature_emb": {
|
||||
@@ -5404,18 +5404,18 @@
|
||||
"unresolvedFailureCount": 6446
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 3535,
|
||||
"attributableFailureCount": 3537,
|
||||
"decisionFailureRate": 0.9757,
|
||||
"decisionSuccessRate": 0.0243,
|
||||
"decisionTotal": 3623,
|
||||
"decisionTotal": 3625,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1492,
|
||||
"architecture_compatibility": 112,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 84,
|
||||
"context_length": 161,
|
||||
"framework_architecture_unsupported": 1304,
|
||||
"memory_capacity": 721,
|
||||
"framework_architecture_unsupported": 1305,
|
||||
"memory_capacity": 722,
|
||||
"model_load": 207,
|
||||
"platform_infrastructure": 865,
|
||||
"repository_structure": 470,
|
||||
@@ -5423,14 +5423,14 @@
|
||||
"tokenizer_compatibility": 411,
|
||||
"参数/模板问题": 45
|
||||
},
|
||||
"failureCount": 5937,
|
||||
"failureCount": 5939,
|
||||
"failureRate": 0.9854,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 865,
|
||||
"successCount": 88,
|
||||
"successRate": 0.0146,
|
||||
"total": 6025,
|
||||
"total": 6027,
|
||||
"unresolvedFailureCount": 1537
|
||||
},
|
||||
"vllm-customized": {
|
||||
@@ -5550,15 +5550,15 @@
|
||||
"unresolvedFailureCount": 196
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
"attributableFailureCount": 73,
|
||||
"decisionFailureRate": 0.9733,
|
||||
"decisionSuccessRate": 0.0267,
|
||||
"decisionTotal": 75,
|
||||
"attributableFailureCount": 74,
|
||||
"decisionFailureRate": 0.9737,
|
||||
"decisionSuccessRate": 0.0263,
|
||||
"decisionTotal": 76,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 70,
|
||||
"ambiguous_runtime": 71,
|
||||
"backend_operator": 1,
|
||||
"context_length": 3,
|
||||
"framework_architecture_unsupported": 62,
|
||||
"framework_architecture_unsupported": 63,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 2,
|
||||
"platform_infrastructure": 1,
|
||||
@@ -5566,18 +5566,18 @@
|
||||
"tokenizer_compatibility": 1,
|
||||
"参数/模板问题": 27
|
||||
},
|
||||
"failureCount": 171,
|
||||
"failureRate": 0.9884,
|
||||
"failureCount": 173,
|
||||
"failureRate": 0.9886,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0116,
|
||||
"total": 173,
|
||||
"unresolvedFailureCount": 97
|
||||
"successRate": 0.0114,
|
||||
"total": 175,
|
||||
"unresolvedFailureCount": 98
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-21T17:41:29.141921+00:00",
|
||||
"generatedAt": "2026-09-21T18:00:40.479875+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 99,
|
||||
@@ -5606,15 +5606,15 @@
|
||||
"unresolvedFailureCount": 161
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"attributableFailureCount": 318,
|
||||
"decisionFailureRate": 0.8346,
|
||||
"decisionSuccessRate": 0.1654,
|
||||
"decisionTotal": 381,
|
||||
"attributableFailureCount": 321,
|
||||
"decisionFailureRate": 0.8359,
|
||||
"decisionSuccessRate": 0.1641,
|
||||
"decisionTotal": 384,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 170,
|
||||
"ambiguous_runtime": 171,
|
||||
"context_length": 1,
|
||||
"framework_architecture_unsupported": 176,
|
||||
"memory_capacity": 18,
|
||||
"framework_architecture_unsupported": 178,
|
||||
"memory_capacity": 19,
|
||||
"model_load": 85,
|
||||
"platform_infrastructure": 2,
|
||||
"repository_structure": 28,
|
||||
@@ -5623,15 +5623,15 @@
|
||||
"日志缺失": 14,
|
||||
"验证失败": 175
|
||||
},
|
||||
"failureCount": 947,
|
||||
"failureRate": 0.9376,
|
||||
"failureCount": 951,
|
||||
"failureRate": 0.9379,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 63,
|
||||
"successRate": 0.0624,
|
||||
"total": 1010,
|
||||
"unresolvedFailureCount": 627
|
||||
"successRate": 0.0621,
|
||||
"total": 1014,
|
||||
"unresolvedFailureCount": 628
|
||||
},
|
||||
"Biren_166m": {
|
||||
"attributableFailureCount": 184,
|
||||
@@ -7137,6 +7137,29 @@
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2_moe|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"modelType": "lfm2_moe",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -7189,9 +7212,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4
|
||||
"ambiguous_runtime": 5
|
||||
},
|
||||
"failureCount": 4,
|
||||
"failureCount": 5,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"modelType": "llama",
|
||||
@@ -7203,8 +7226,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 4
|
||||
"total": 5,
|
||||
"unresolvedFailureCount": 5
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|none": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -7668,6 +7691,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation|bailing_hybrid|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"memory_capacity": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "bailing_hybrid",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation|llama|awq": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -7714,6 +7760,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation|muse_glimmer|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "muse_glimmer",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation|qwen3_vl|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -22485,6 +22554,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2_moe|none|33": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
"modelType": "lfm2_moe",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2|none|29": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -22707,9 +22800,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
"ambiguous_runtime": 2
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
@@ -22722,8 +22815,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|none|30": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -23397,6 +23490,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation|bailing_hybrid|none|33": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"memory_capacity": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
"modelType": "bailing_hybrid",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation|llama|awq|30": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -23469,6 +23586,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation|muse_glimmer|none|34": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 34,
|
||||
"modelType": "muse_glimmer",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation|qwen3_vl|none|34": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -36557,21 +36698,21 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 16345,
|
||||
"totalRecords": 16539,
|
||||
"terminalRecords": 16349,
|
||||
"totalRecords": 16543,
|
||||
"totals": {
|
||||
"attributableFailureCount": 5900,
|
||||
"decisionFailureRate": 0.8618,
|
||||
"decisionSuccessRate": 0.1382,
|
||||
"decisionTotal": 6846,
|
||||
"attributableFailureCount": 5903,
|
||||
"decisionFailureRate": 0.8619,
|
||||
"decisionSuccessRate": 0.1381,
|
||||
"decisionTotal": 6849,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3991,
|
||||
"ambiguous_runtime": 3992,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 103,
|
||||
"context_length": 321,
|
||||
"framework_architecture_unsupported": 2081,
|
||||
"memory_capacity": 1198,
|
||||
"framework_architecture_unsupported": 2083,
|
||||
"memory_capacity": 1199,
|
||||
"model_load": 499,
|
||||
"platform_infrastructure": 925,
|
||||
"repository_structure": 739,
|
||||
@@ -36581,31 +36722,31 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 674
|
||||
},
|
||||
"failureCount": 15399,
|
||||
"failureCount": 15403,
|
||||
"failureRate": 0.9421,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 925,
|
||||
"successCount": 946,
|
||||
"successRate": 0.0579,
|
||||
"total": 16345,
|
||||
"unresolvedFailureCount": 8574
|
||||
"total": 16349,
|
||||
"unresolvedFailureCount": 8575
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"组合 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -36645,6 +36786,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 16539,
|
||||
"summarizedRecords": 16543,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -2190,6 +2190,67 @@
|
||||
{"batchId": "72cb9a4a00eb4f81aa0d838e048a300f", "completedAt": "2026-09-21T17:59:07.220187+00:00", "configFingerprint": "58bd440e460cf3e4d9271b3c32c451e80254e59faf47ce55dcda11588cf4117e", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:54:45.272288+00:00", "framework": "vllm", "intentId": "c29a84b01fbd4ee6af79550df0a097f8", "lastModified": "2026-08-24T18:24:11+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "reason": null, "reconciledAt": "2026-09-21T17:59:08.869520+00:00", "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "5005091", "taskType": "text-generation"}
|
||||
{"batchId": "72cb9a4a00eb4f81aa0d838e048a300f", "completedAt": "2026-09-21T17:59:07.220190+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:54:45.272346+00:00", "framework": "vllm", "intentId": "439fc9c1e671466b944c30d87b849d94", "lastModified": "2026-08-24T17:55:20+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token", "reason": null, "reconciledAt": "2026-09-21T17:59:08.869055+00:00", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "5005092", "taskType": "text-generation"}
|
||||
{"batchId": "72cb9a4a00eb4f81aa0d838e048a300f", "completedAt": "2026-09-21T17:59:07.220192+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:54:45.272404+00:00", "framework": "vllm", "intentId": "5d0cb35457014256a231f3dff64bf6ad", "lastModified": "2026-09-12T12:30:14+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "reason": null, "reconciledAt": "2026-09-21T17:59:08.868472+00:00", "repoId": "OpenBMB/MiniCPM5-2B-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_bi-150", "taskId": "5005093", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.213781+00:00", "framework": "vllm_tokenizer_patch", "intentId": "db7b43e9ab3e44c78750def79629f872", "lastModified": "2026-08-24T15:14:56+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/SmolLM-135M-Instruct-quantized.w4a16", "repoId": "nm-testing/SmolLM-135M-Instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.213958+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4daa222bafcd45738690db6f36bcab64", "lastModified": "2026-08-24T16:38:03+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t", "repoId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.214052+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3c81ccfc8641416781f211e2db65fcee", "lastModified": "2026-08-24T15:42:55+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8-channel-a8-tensor", "repoId": "nm-testing/tinyllama-oneshot-w8-channel-a8-tensor", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.214141+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e41c11bd33754d7b8fd7cb4884703cc4", "lastModified": "2026-08-24T15:48:56+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2-asym", "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2-asym", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.214230+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0c57f9d9e63740daa308707843ecddf6", "lastModified": "2026-08-24T17:35:14+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-llama3-8b-Instruct-SmoothQuant-Fp8", "repoId": "nm-testing/Meta-llama3-8b-Instruct-SmoothQuant-Fp8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.214317+00:00", "framework": "vllm_tokenizer_patch", "intentId": "654af64758bf449c98b09ebd5a2b4e08", "lastModified": "2026-08-24T17:33:00+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test-bos", "repoId": "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test-bos", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.214405+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5b0f862fbe9a4012a55ac6ee6a72ecb6", "lastModified": "2026-08-24T17:58:05+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-one-shot-w4a16-group-packed", "repoId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.214482+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c8f2268669d34a5c959d9107daf8839f", "lastModified": "2026-08-24T16:17:12+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2", "repoId": "nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.214557+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e17aa3e5748141ec8e6b4733ee31e48e", "lastModified": "2026-08-24T17:41:35+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test", "repoId": "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.214632+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0a80c042fd8f4c8b81cbb504f6d789a2", "lastModified": "2026-08-24T14:45:05+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.214795+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cb85ea72e7b94f0c933cb6fe8eb3ebc2", "lastModified": "2026-08-24T16:10:08+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w4a16-channel-v2", "repoId": "nm-testing/tinyllama-oneshot-w4a16-channel-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.214874+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3cdec3f9290344329987416daf1873f1", "lastModified": "2026-08-24T15:07:56+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Qwen2-1.5B-Instruct-FP8W8", "repoId": "nm-testing/Qwen2-1.5B-Instruct-FP8W8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.214950+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b3c7f12c69194cd1bba59204f214a6e6", "lastModified": "2026-08-24T19:10:38+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.215024+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2c20fe70e4474c86b48dfb902055185f", "lastModified": "2026-08-24T16:03:28+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "repoId": "nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.215092+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5e8ad38e922f4b13bee54b034074cb40", "lastModified": "2026-08-24T16:35:49+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.215159+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0fe649cae6ce4904862627c2d651f645", "lastModified": "2026-08-24T16:01:21+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w4a16-group128-v2", "repoId": "nm-testing/tinyllama-oneshot-w4a16-group128-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.215225+00:00", "framework": "vllm_tokenizer_patch", "intentId": "caf9cba4f83c4dab9a9feba0803233b5", "lastModified": "2026-08-24T17:49:53+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.215290+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e2c8789d8ec6421d88ef2fd0b78c0524", "lastModified": "2026-08-24T16:40:22+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.215356+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6361e41718334851a26e5bb8122ab508", "lastModified": "2026-08-24T17:53:32+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-llama3-8b-Instruct-quant-FP8", "repoId": "nm-testing/Meta-llama3-8b-Instruct-quant-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.215421+00:00", "framework": "vllm-mlu", "intentId": "fde47dff96714c18813d2831df64e1b6", "lastModified": "2026-08-24T19:21:33+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a8", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.215538+00:00", "framework": "vllm_tokenizer_patch", "intentId": "57f56887cb0c47cb99537a517f6aec0b", "lastModified": "2026-08-24T19:26:17+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w4a16", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.215649+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e991be4b77304839bd9f41217411ae9d", "lastModified": "2026-08-24T17:02:50+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "repoId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.215741+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7f994eb0e2994cee8caa26988666664f", "lastModified": "2026-08-24T18:12:10+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.215827+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e858e50a015f4a98891b1f5af8ad7e66", "lastModified": "2026-08-24T18:26:59+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/nonuniform", "repoId": "nm-testing/nonuniform", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.215912+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0ac1e3e15eb74638bea20f57a161efae", "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": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.215998+00:00", "framework": "vllm_tokenizer_patch", "intentId": "352f2b816d654ba6961c19a38a80983b", "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": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.216084+00:00", "framework": "vllm_tokenizer_patch", "intentId": "27b170c7d68245248f38247c478544f3", "lastModified": "2026-08-24T19:36:07+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.216169+00:00", "framework": "vllm_tokenizer_patch", "intentId": "af1563f944d44564ba224320fcdd9269", "lastModified": "2026-09-11T15:37:46+00:00", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-base-32K", "repoId": "CohereLabs/tiny-aya-base-32K", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.216255+00:00", "framework": "vllm", "intentId": "7338af8e19e54e92acf847d4720f171c", "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": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.216357+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7495556f35b44d93bc0dbf69c1aa1360", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.216432+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c72df26d9881474d807b800c370118da", "lastModified": "2026-08-24T19:34:25+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.216508+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0d3837a9fd704afbb56b5ac83beb1bb9", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.216584+00:00", "framework": "vllm_fix_tokenizer", "intentId": "272f1f4c4ac14242ba4c58416bef3100", "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, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.216659+00:00", "framework": "vllm_fix_tokenizer", "intentId": "833d042cd66941c39f777f0cbce002bb", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.216742+00:00", "framework": "vllm_fix_tokenizer", "intentId": "59d3c7a567e840ab890c38e15ae7a375", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.216817+00:00", "framework": "vllm_fix_tokenizer", "intentId": "257a85c3092745b4acb3513697133545", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.216890+00:00", "framework": "vllm_fix_tokenizer", "intentId": "404318b1ea8744fbbffea142d4255dbc", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.216965+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a685a0c1c5a3484d88a7ad4ff9dfa5d3", "lastModified": "2026-08-24T19:39:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.217040+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ea115207309148c9b91e1f27aba8860f", "lastModified": "2026-08-24T18:09:20+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "repoId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.217114+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0d3044b0193f4acd99dde045f9caa021", "lastModified": "2026-08-24T18:26:39+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-static-v2", "repoId": "nm-testing/tinyllama-oneshot-w8a8-static-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.217190+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8818199809db4bd68492042608efaabd", "lastModified": "2026-08-24T18:28:40+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-marlin24-w4a16-group128", "repoId": "nm-testing/tinyllama-marlin24-w4a16-group128", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.217266+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d243f3bf72124680925200f48f1c6a23", "lastModified": "2026-08-24T18:24:11+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.217341+00:00", "framework": "vllm_fix_tokenizer", "intentId": "04c169319da44707b0b65f2c696905aa", "lastModified": "2026-08-24T18:06:52+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3.1-8B-Instruct-FP8-hf", "repoId": "nm-testing/Meta-Llama-3.1-8B-Instruct-FP8-hf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.217416+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f51a3a79128a4b1abdc3ed1a095047a3", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.217491+00:00", "framework": "vllm_fix_tokenizer", "intentId": "750cded6318646e6988921e48664644e", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.217566+00:00", "framework": "vllm_fix_tokenizer", "intentId": "20019d7d88c5487f8a705cdebcfc3321", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.217642+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e75e8e12b57c47fe92b7b4882b9d4449", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.217724+00:00", "framework": "vllm_fix_tokenizer", "intentId": "922f12ebb7a945ae9e8b65757ec84fee", "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": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.217799+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1fc38ffcc03a4762a4885281b46e85be", "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": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.217875+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f922d18700464577944a50b77bfad45e", "lastModified": "2026-09-03T18:32:29+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Apodex-1.1-mini-AWQ-INT4", "repoId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.217949+00:00", "framework": "vllm_fix_tokenizer", "intentId": "90ed1511bfa44aa19fee01dd8059f302", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.218024+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f3f7547809924ba183855a98f299f1bd", "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": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.218100+00:00", "framework": "vllm_fix_tokenizer", "intentId": "26ad390474c3453890d82b6980e3bd08", "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": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.218175+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4138017fa814408c9fa55e57d6a3a0c9", "lastModified": "2026-08-26T19:32:38+00:00", "modelAddress": "https://modelscope.cn/models/pfnet/plamo-3-nict-8b-base", "repoId": "pfnet/plamo-3-nict-8b-base", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.218250+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4f716c76f9b44b77ba3a68ec037867f6", "lastModified": "2026-09-09T06:50:48+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.218324+00:00", "framework": "transformers", "intentId": "9fa149af1c2f456780b69d7555a46f66", "lastModified": "2026-08-24T22:55:11+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/AquilaMed-RL", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.218437+00:00", "framework": "transformers", "intentId": "456dd385497d4b14bc36f2d3288b3bbe", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.218549+00:00", "framework": "transformers", "intentId": "2d573356843f47688078eb0522fed710", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.218660+00:00", "framework": "transformers", "intentId": "e31a762c77db4923b89859d34b2ba3e7", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "0335c7e4668aaa963303ebe91f80d6eb1e7e8d0299011bd85f7e05a4df031dc7", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.218778+00:00", "framework": "transformers", "intentId": "78e7038f452b4eda97009ee415a5fd1e", "lastModified": "2026-08-24T18:26:53+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a16-per-channel", "repoId": "nm-testing/tinyllama-oneshot-w8a16-per-channel", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "423f8e5216844b2bb18d769589b90bb6", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T18:02:36.218890+00:00", "framework": "transformers", "intentId": "178463e4292248a991872bf60db88e6c", "lastModified": "2026-09-10T07:52:22+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "72cb9a4a00eb4f81aa0d838e048a300f", "completedAt": "2026-09-21T17:59:07.220197+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:54:45.272511+00:00", "framework": "vllm", "intentId": "be47445997a84274a977bda0acc69d55", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
|
||||
{"batchId": "72cb9a4a00eb4f81aa0d838e048a300f", "completedAt": "2026-09-21T17:59:07.220195+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:54:45.272454+00:00", "framework": "vllm", "intentId": "874d32bd63454936b057f3f5a154fe5e", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
|
||||
{"batchId": "72cb9a4a00eb4f81aa0d838e048a300f", "completedAt": "2026-09-21T17:59:07.220184+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:54:45.272231+00:00", "framework": "vllm", "intentId": "875c0667c0994331a5616d5e3df41574", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
|
||||
|
||||
@@ -2,24 +2,24 @@
|
||||
"agentVersion": "2026.09.20.2",
|
||||
"checksums": {
|
||||
".modelhub_state/account_capacity.json": "68d2a8390ad022f2ddcd30841f3860c4535387fa64cb46dc7507eb16837e798f",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "7f4a603cda7ec7d310f1368605ae4674e05947d76f0c04f314fea5df431cd698",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "ebb61458645619ed3e9714128a1948fc989ece15c44f4b4bdfa5c5f64ec450df",
|
||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||
".modelhub_state/market_intelligence.json": "26b43d405f1e504096d7e63df7368958fd583204bc75d4810efa0f1d531858f8",
|
||||
".modelhub_state/official_capabilities.json": "6e6496f27ab1784da148a25c166df1ddd398ef990dbfc68b7b6a519f50938f26",
|
||||
".modelhub_state/outcome_checkpoint.json": "876802dbd40119e6f9741e48700b8811927fd8f15657a5f0e2d1fe6445fddf81",
|
||||
".modelhub_state/market_intelligence.json": "4b7c1354c8c2f3ea55e031cd5fc86ea787377dbcf524e2a30f9f74b9b3da31fe",
|
||||
".modelhub_state/official_capabilities.json": "f05f138d6be9a3ff5383ba7556a510e588ff25f455fda5dec8e5ad7805f63b0c",
|
||||
".modelhub_state/outcome_checkpoint.json": "e797999d81d19c5d3caee283a853bb839de96fd5ba4f40f360563babad75449c",
|
||||
".modelhub_state/queue_cleanup_latest.json": "96de561331568d32afa16a3d1299e6bf6ad1009a8239697991dc48f28baf298b",
|
||||
".modelhub_state/recent_outcomes.jsonl": "0ccec2ea3b1605a1198ac76ae46544d954bc4ef98ee1287cee8dd9c284deb057",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "d088a1bea84c51cc7a56fc1b2eea947cb05bf64198f2d792d7b8450f609f32c5",
|
||||
".modelhub_state/recovery_intents.jsonl": "8cdfaa2155caf51a6d95cfc379db0556f807420da84cc6041155807bd4d54851",
|
||||
".modelhub_state/recovery_intents.jsonl": "091035193eb50c286a14bd9271b502d1affeda13d89511db9c7a2c628442517a",
|
||||
".modelhub_state/routing_intelligence.json": "86a4cadd22b067497ee6b19768bbece52eba69396da415decad65dfc2274936c",
|
||||
".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
|
||||
".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7",
|
||||
"ledger/submissions.jsonl": "4c5e0c49d178d75a18de174114e86524aecd30eeba31932fb09f4a7ccd435c10",
|
||||
"outcomes/submissions.jsonl": "8990eb327ce3f59be4d82592ec3226d44e4d1efc71fbfa2bc8271758cffc55dd"
|
||||
"outcomes/submissions.jsonl": "8c3e6da447b44ba3313af94a6ca928a3f6bceb8ada1658f3670ec58caa0bdaa0"
|
||||
},
|
||||
"generation": 11593,
|
||||
"phase": "cycle",
|
||||
"generation": 11594,
|
||||
"phase": "intent",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-21T17:59:36.829562+00:00",
|
||||
"updatedAt": "2026-09-21T18:02:36.403223+00:00",
|
||||
"writerId": "8b35139af6674067a339a670222d4b67"
|
||||
}
|
||||
|
||||
@@ -381,7 +381,6 @@
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:00:25.647805+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736540899, "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": 13756990943, "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": 13756990943}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:52.247958+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969088", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:00:25.647605+00:00", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11002488632, "estimatedRequiredGiB": 12.322, "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": 10176447713, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6340437856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:2-bit", "custom_tag:quantization", "custom_tag:escha", "custom_tag:sglang", "custom_tag:code", "custom_tag:reasoning", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "escha", "repositoryOnDiskBytes": 11025855102}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:52.244608+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969089", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:00:25.647652+00:00", "modelId": "aisingapore/Llama-SEA-LION-v3.5-8B-R", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16060556344, "estimatedRequiredGiB": 17.97, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 16079585018, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16079585018}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:52.306108+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969091", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:10:38.766176+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16936006912, "estimatedRequiredGiB": 18.948, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 16953948786, "modelscopeLicense": "other", "modelscopeParams": 8467856832, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "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": 16953948786}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:11.550122+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969304", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:10:38.766123+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "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": 17788663591, "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": 17788663591}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:11.551543+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969307", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T11:10:38.766220+00:00", "modelId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7486327132, "estimatedRequiredGiB": 8.403, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 7518908360, "modelscopeLicense": "gemma", "modelscopeParams": 2227418442, "modelscopeTags": ["license:gemma", "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:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7518908360}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:11.547157+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969306", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T11:10:38.766264+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:17.666037+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969308", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -426,7 +425,6 @@
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600433+00:00", "modelId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8308282608, "estimatedRequiredGiB": 9.319, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 8338221588, "modelscopeLicense": "llama2", "modelscopeParams": 12247782400, "modelscopeTags": ["license:llama2", "model_type:mistral", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8338221588}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:24:23.586939+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969576", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600240+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "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": 663410366, "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", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663410366}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:24:23.730955+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969577", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600371+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663591, "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": 17788663591}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:24:23.751982+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969579", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600428+00:00", "modelId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "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": 9093325202, "modelscopeLicense": "llama3", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093325202}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:24.191660+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969616", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600358+00:00", "modelId": "neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8708787584, "estimatedRequiredGiB": 9.746, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 8720442075, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7615616512, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8720442075}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:24.243163+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969622", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.599757+00:00", "modelId": "RedHatAI/starcoder2-7b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857298896, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860673720, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 7400416256, "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": 7860673720}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:24.195140+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969615", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T11:30:54.600185+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": "2026-09-20T03:25:24.241562+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969620", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -466,13 +464,11 @@
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600197+00:00", "modelId": "IntervitensInc/kek_mk3", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3289069288, "estimatedRequiredGiB": 3.683, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 3295875324, "modelscopeLicense": null, "modelscopeParams": 1644515328, "modelscopeTags": ["model_type:stablelm", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3295875324}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:30:23.839811+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969805", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.600320+00:00", "modelId": "sbintuitions/sarashina2.2-3b-instruct-v0.1", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6711252896, "estimatedRequiredGiB": 7.503, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "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": "2026-09-20T03:30:23.758933+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4969807", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.599773+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "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": "2026-09-20T03:30:23.763321+00:00", "targetGpu": "MetaX_c-500", "taskId": "4969808", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.599954+00:00", "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15787992416, "estimatedRequiredGiB": 17.659, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 15801179822, "modelscopeLicense": "mit", "modelscopeParams": 7893392800, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15801179822}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:30:31.139946+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969809", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.600313+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727938576, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737300809, "modelscopeLicense": "other", "modelscopeParams": 8030261248, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737300809}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:30:31.137775+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969811", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.600377+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:30:31.143975+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969815", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.600145+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737318602}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:30:31.135514+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969816", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.599901+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 7550622334}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:30:31.145680+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969814", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.599690+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:30:31.146899+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969812", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.599765+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21407235494, "estimatedRequiredGiB": 23.956, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 21435726263, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5792290816, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21435726263}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:30:31.141968+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969818", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.600253+00:00", "modelId": "whcl412/mlx-LycheeAI-coder-1.7b", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 968080210, "estimatedRequiredGiB": 1.095, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 979581804, "modelscopeLicense": "apache-2.0", "modelscopeParams": 268944384, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:coder", "custom_tag:lora", "custom_tag:code", "custom_tag:lychee", "custom_tag:finetune", "custom_tag:multilingual"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 979581804}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:30:31.153489+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969817", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T12:01:00.671231+00:00", "modelId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093325202, "modelscopeLicense": "llama3", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093325202}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:40:37.351352+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969964", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T12:01:00.670537+00:00", "modelId": "neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8708787584, "estimatedRequiredGiB": 9.746, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 8720442075, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7615616512, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8720442075}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:40:37.293456+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969956", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -1005,10 +1001,10 @@
|
||||
{"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-21T17:41:26.757156+00:00", "modelId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10261168632, "estimatedRequiredGiB": 11.478, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 10270608122, "modelscopeLicense": "other", "modelscopeParams": 16754741248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible - mergekit - merge - facebook - meta - pytorch - llama - llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 10270608122}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T09:33:26.659264+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4998167", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T17:41:26.757091+00:00", "modelId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1047023664, "estimatedRequiredGiB": 1.172, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1048871402, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1048871402}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T09:40:34.489077+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4998299", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T17:41:26.757131+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013064, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093197403, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093197403}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T09:40:34.490655+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4998300", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/gemma-2-2b-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6746735136, "estimatedRequiredGiB": 7.565, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 6768615358, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6768615358}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T09:41:35.705044+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4998344", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-7b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7855165704, "estimatedRequiredGiB": 8.783, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7858541078, "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": 7858541078}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T09:45:53.481324+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4998407", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-7b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857298896, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860673858, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 7400416256, "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": 7860673858}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T09:46:02.415434+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4998415", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-09-21T09:49:55.866013+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4998525", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T18:00:38.063615+00:00", "modelId": "RedHatAI/gemma-2-2b-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6746735136, "estimatedRequiredGiB": 7.565, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 6768615358, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6768615358}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T09:41:35.705044+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4998344", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-21T18:00:38.063679+00:00", "modelId": "neuralmagic/starcoder2-7b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7855165704, "estimatedRequiredGiB": 8.783, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7858541078, "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": 7858541078}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T09:45:53.481324+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4998407", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-21T18:00:38.063692+00:00", "modelId": "neuralmagic/starcoder2-7b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857298896, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860673858, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 7400416256, "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": 7860673858}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T09:46:02.415434+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4998415", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-21T18:00:38.063651+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "waiting", "submitTime": "2026-09-21T09:49:55.866013+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4998525", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-3b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093158536, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 4096457730, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 3181366272, "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": 4096457730}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T10:13:37.540416+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4998917", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "aisingapore/SEA-LION-v1-7B-IT-Research", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361968, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": "pending", "submitTime": "2026-09-21T10:17:52.663711+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4999054", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "nm-testing/Meta-Llama-3.1-8B-Instruct-FP8-hf", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090504988, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9090504988}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T10:23:46.162420+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4999147", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user