state: generation 6888 (cycle)

This commit is contained in:
2026-09-13 21:11:30 +00:00
parent b2a07bb14d
commit e1308fbb55
12 changed files with 2526 additions and 2158 deletions

View File

@@ -1079,17 +1079,19 @@
"sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|model_type:mellum": {
"architectureSignature": "model_type:mellum",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-12T02:35:21+00:00",
"evidenceCount": 2,
"expiresAt": "2026-10-13T21:09:21+00:00",
"framework": "vllm_fix_tokenizer",
"latestFailureAt": "2026-09-12T02:35:21+00:00",
"latestFailureAt": "2026-09-13T21:09:21+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "mellum",
"sourceModelIds": [
"JetBrains/Mellum2-12B-A2.5B-Instruct",
"JetBrains/Mellum2-12B-A2.5B-Thinking"
],
"sourceTaskIds": [
"4152538",
"4152611"
],
"targetGpu": "Sunrise_pt-200-x1",
@@ -1118,17 +1120,36 @@
"architectureSignature": "model_type:qwen3_5",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-08T12:15:21+00:00",
"expiresAt": "2026-10-13T21:01:21+00:00",
"framework": "vllm_fix_tokenizer",
"latestFailureAt": "2026-09-08T12:15:21+00:00",
"latestFailureAt": "2026-09-13T21:01:21+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "qwen3_5",
"sourceModelIds": [
"iic/UEmbed-4B"
"Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16"
],
"sourceTaskIds": [
"4152744"
"4336358"
],
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation"
},
"sunrise_pt-200-x1|vllm|text-generation|model_type:qwen3_5_moe": {
"architectureSignature": "model_type:qwen3_5_moe",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-13T21:05:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-13T21:05:21+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "qwen3_5_moe",
"sourceModelIds": [
"mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B"
],
"sourceTaskIds": [
"4490277"
],
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation"
@@ -1473,9 +1494,9 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-13T21:08:24.145867+00:00",
"generatedAt": "2026-09-13T21:11:29.499929+00:00",
"summary": {
"activeBlockCount": 74,
"activeBlockCount": 75,
"byGpuFramework": {
"Ascend_910-b3|vllm": 9,
"Ascend_910-b4|vllm": 10,
@@ -1484,7 +1505,7 @@
"Iluvatar_bi-150|vllm": 4,
"MetaX_c-500|vllm": 7,
"Mthreads_s4000|vllm": 7,
"Sunrise_pt-200-x1|vllm": 1,
"Sunrise_pt-200-x1|vllm": 2,
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 3,
"Vastai_va16|vllm": 14,
"Vastai_va16|vllm_fix_tokenizer": 2,

View File

@@ -11,7 +11,7 @@
"1": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 500,
"listingErrors": 501,
"nextPage": 1,
"recordsScanned": 0,
"uniqueRecords": 0
@@ -102,12 +102,12 @@
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
"failureLogsInspected": 0,
"mode": "incremental_decision_only",
"nextAccountIndex": 1,
"nextAccountIndex": 2,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-13T21:08:24.120747+00:00",
"updatedAt": "2026-09-13T21:11:29.473387+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-13T21:06:53.337104+00:00",
"generatedAt": "2026-09-13T21:09:38.816633+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-13T20:14:37.132877+00:00",
"lastSyncTime": "2026-09-13T20:14:36.914736+00:00",
"generatedAt": "2026-09-13T21:09:38.788660+00:00",
"lastSyncTime": "2026-09-13T21:09:38.757189+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1083,17 +1083,19 @@
"sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|model_type:mellum": {
"architectureSignature": "model_type:mellum",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-12T02:35:21+00:00",
"evidenceCount": 2,
"expiresAt": "2026-10-13T21:09:21+00:00",
"framework": "vllm_fix_tokenizer",
"latestFailureAt": "2026-09-12T02:35:21+00:00",
"latestFailureAt": "2026-09-13T21:09:21+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "mellum",
"sourceModelIds": [
"JetBrains/Mellum2-12B-A2.5B-Instruct",
"JetBrains/Mellum2-12B-A2.5B-Thinking"
],
"sourceTaskIds": [
"4152538",
"4152611"
],
"targetGpu": "Sunrise_pt-200-x1",
@@ -1122,17 +1124,36 @@
"architectureSignature": "model_type:qwen3_5",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-08T12:15:21+00:00",
"expiresAt": "2026-10-13T21:01:21+00:00",
"framework": "vllm_fix_tokenizer",
"latestFailureAt": "2026-09-08T12:15:21+00:00",
"latestFailureAt": "2026-09-13T21:01:21+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "qwen3_5",
"sourceModelIds": [
"iic/UEmbed-4B"
"Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16"
],
"sourceTaskIds": [
"4152744"
"4336358"
],
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation"
},
"sunrise_pt-200-x1|vllm|text-generation|model_type:qwen3_5_moe": {
"architectureSignature": "model_type:qwen3_5_moe",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-13T21:05:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-13T21:05:21+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "qwen3_5_moe",
"sourceModelIds": [
"mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B"
],
"sourceTaskIds": [
"4490277"
],
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation"
@@ -1478,7 +1499,7 @@
}
},
"architectureCompatibilitySummary": {
"activeBlockCount": 74,
"activeBlockCount": 75,
"byGpuFramework": {
"Ascend_910-b3|vllm": 9,
"Ascend_910-b4|vllm": 10,
@@ -1487,7 +1508,7 @@
"Iluvatar_bi-150|vllm": 4,
"MetaX_c-500|vllm": 7,
"Mthreads_s4000|vllm": 7,
"Sunrise_pt-200-x1|vllm": 1,
"Sunrise_pt-200-x1|vllm": 2,
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 3,
"Vastai_va16|vllm": 14,
"Vastai_va16|vllm_fix_tokenizer": 2,
@@ -1982,15 +2003,15 @@
"unresolvedFailureCount": 70
},
"Iluvatar_mrv-100|vllm|text-generation": {
"attributableFailureCount": 2,
"attributableFailureCount": 3,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {
"framework_architecture_unsupported": 1,
"framework_architecture_unsupported": 2,
"model_load": 1
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2000,7 +2021,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -2233,43 +2254,43 @@
"unresolvedFailureCount": 34
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 46,
"attributableFailureCount": 49,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 46,
"decisionTotal": 49,
"failureBreakdown": {
"backend_operator": 2,
"framework_architecture_unsupported": 4,
"platform_infrastructure": 2,
"tokenizer_compatibility": 40,
"framework_architecture_unsupported": 6,
"platform_infrastructure": 3,
"tokenizer_compatibility": 41,
"参数/模板问题": 6
},
"failureCount": 54,
"failureCount": 58,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"platformFailureCount": 3,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 54,
"total": 58,
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 5,
"attributableFailureCount": 6,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 1,
"framework_architecture_unsupported": 2,
"platform_infrastructure": 1,
"tokenizer_compatibility": 4,
"参数/模板问题": 2
},
"failureCount": 9,
"failureCount": 10,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2279,7 +2300,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 9,
"total": 10,
"unresolvedFailureCount": 3
},
"Vastai_va16|unknown|text-generation": {
@@ -2508,14 +2529,14 @@
"unresolvedFailureCount": 877
},
"vllm": {
"attributableFailureCount": 299,
"attributableFailureCount": 301,
"decisionFailureRate": 0.9901,
"decisionSuccessRate": 0.0099,
"decisionTotal": 302,
"decisionTotal": 304,
"failureBreakdown": {
"ambiguous_runtime": 201,
"backend_operator": 34,
"framework_architecture_unsupported": 212,
"framework_architecture_unsupported": 214,
"memory_capacity": 6,
"model_load": 26,
"platform_infrastructure": 1,
@@ -2524,14 +2545,14 @@
"tokenizer_compatibility": 7,
"参数/模板问题": 24
},
"failureCount": 525,
"failureCount": 527,
"failureRate": 0.9943,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0057,
"total": 528,
"total": 530,
"unresolvedFailureCount": 225
},
"vllm-mlu": {
@@ -2594,27 +2615,27 @@
"unresolvedFailureCount": 4
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 49,
"attributableFailureCount": 52,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 49,
"decisionTotal": 52,
"failureBreakdown": {
"ambiguous_runtime": 37,
"backend_operator": 2,
"framework_architecture_unsupported": 6,
"framework_architecture_unsupported": 8,
"model_load": 1,
"platform_infrastructure": 2,
"tokenizer_compatibility": 40,
"platform_infrastructure": 3,
"tokenizer_compatibility": 41,
"参数/模板问题": 7
},
"failureCount": 95,
"failureCount": 99,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"platformFailureCount": 3,
"successCount": 0,
"successRate": 0.0,
"total": 95,
"total": 99,
"unresolvedFailureCount": 44
},
"vllm_tokenizer_patch": {
@@ -2636,7 +2657,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-13T20:14:37.128504+00:00",
"generatedAt": "2026-09-13T21:09:38.784533+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 31,
@@ -2800,27 +2821,27 @@
"unresolvedFailureCount": 44
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 97,
"decisionFailureRate": 0.8661,
"decisionSuccessRate": 0.1339,
"decisionTotal": 112,
"attributableFailureCount": 98,
"decisionFailureRate": 0.8673,
"decisionSuccessRate": 0.1327,
"decisionTotal": 113,
"failureBreakdown": {
"ambiguous_runtime": 21,
"framework_architecture_unsupported": 53,
"framework_architecture_unsupported": 54,
"memory_capacity": 1,
"model_load": 43,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 168,
"failureRate": 0.918,
"failureCount": 169,
"failureRate": 0.9185,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 15,
"successRate": 0.082,
"total": 183,
"successRate": 0.0815,
"total": 184,
"unresolvedFailureCount": 70
},
"Kunlunxin_p-800": {
@@ -2896,27 +2917,27 @@
"unresolvedFailureCount": 77
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 51,
"decisionFailureRate": 0.9808,
"decisionSuccessRate": 0.0192,
"decisionTotal": 52,
"attributableFailureCount": 55,
"decisionFailureRate": 0.9821,
"decisionSuccessRate": 0.0179,
"decisionTotal": 56,
"failureBreakdown": {
"ambiguous_runtime": 1,
"backend_operator": 2,
"framework_architecture_unsupported": 5,
"platform_infrastructure": 3,
"tokenizer_compatibility": 44,
"framework_architecture_unsupported": 8,
"platform_infrastructure": 4,
"tokenizer_compatibility": 45,
"参数/模板问题": 10,
"验证失败": 32
},
"failureCount": 97,
"failureRate": 0.9898,
"failureCount": 102,
"failureRate": 0.9903,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"platformFailureCount": 4,
"successCount": 1,
"successRate": 0.0102,
"total": 98,
"successRate": 0.0097,
"total": 103,
"unresolvedFailureCount": 43
},
"Vastai_va16": {
@@ -2982,7 +3003,7 @@
"hygon_k100-ai": 64.0
},
"pendingRecords": 0,
"policyCancelledRecords": 87,
"policyCancelledRecords": 93,
"profileCombinationStats": {
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2|none": {
"attributableFailureCount": 0,
@@ -3534,6 +3555,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|rwkv7|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "rwkv7",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|zaya|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -4201,6 +4245,29 @@
"total": 3,
"unresolvedFailureCount": 3
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"tokenizer_compatibility": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "gemma2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|hrm_text|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -4580,19 +4647,19 @@
"unresolvedFailureCount": 12
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 10,
"consecutiveFailures": 10,
"attributableFailureCount": 9,
"consecutiveFailures": 9,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 10,
"decisionTotal": 9,
"failureBreakdown": {
"ambiguous_runtime": 10,
"backend_operator": 4,
"backend_operator": 3,
"framework_architecture_unsupported": 5,
"model_load": 1
},
"failureCount": 20,
"failureCount": 19,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
@@ -4604,7 +4671,7 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 20,
"total": 19,
"unresolvedFailureCount": 10
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -4710,20 +4777,20 @@
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 13,
"consecutiveFailures": 13,
"attributableFailureCount": 12,
"consecutiveFailures": 12,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 13,
"decisionTotal": 12,
"failureBreakdown": {
"ambiguous_runtime": 1,
"backend_operator": 2,
"backend_operator": 1,
"framework_architecture_unsupported": 7,
"model_load": 3,
"repository_structure": 1
},
"failureCount": 14,
"failureCount": 13,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4735,7 +4802,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 14,
"total": 13,
"unresolvedFailureCount": 1
},
"Iluvatar_mrv-100|unknown|text-generation": {
@@ -4921,52 +4988,52 @@
"unresolvedFailureCount": 1
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 15,
"consecutiveFailures": 15,
"attributableFailureCount": 16,
"consecutiveFailures": 16,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 15,
"decisionTotal": 16,
"failureBreakdown": {
"framework_architecture_unsupported": 2,
"platform_infrastructure": 1,
"tokenizer_compatibility": 13
"framework_architecture_unsupported": 4,
"platform_infrastructure": 2,
"tokenizer_compatibility": 12
},
"failureCount": 16,
"failureCount": 18,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": "2026-09-10T11:01:21+00:00",
"lastTerminalAt": "2026-09-13T04:05:56.910823+00:00",
"lastPlatformFailureAt": "2026-09-13T21:01:21+00:00",
"lastTerminalAt": "2026-09-13T21:09:24.912761+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"platformFailureCount": 2,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 16,
"total": 18,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 1,
"platform_infrastructure": 1,
"framework_architecture_unsupported": 1,
"tokenizer_compatibility": 3
},
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": "2026-09-09T17:17:21+00:00",
"lastTerminalAt": "2026-09-13T05:03:23.648954+00:00",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-13T21:09:24.912775+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
@@ -5968,6 +6035,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|rwkv7|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "rwkv7",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|zaya|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -7142,6 +7233,30 @@
"total": 3,
"unresolvedFailureCount": 3
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"tokenizer_compatibility": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 33,
"modelType": "gemma2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|hrm_text|none|31": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -7479,34 +7594,34 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1779,
"totalRecords": 1866,
"terminalRecords": 1785,
"totalRecords": 1878,
"totals": {
"attributableFailureCount": 523,
"decisionFailureRate": 0.8986,
"decisionSuccessRate": 0.1014,
"decisionTotal": 582,
"attributableFailureCount": 528,
"decisionFailureRate": 0.8995,
"decisionSuccessRate": 0.1005,
"decisionTotal": 587,
"failureBreakdown": {
"ambiguous_runtime": 417,
"backend_operator": 43,
"framework_architecture_unsupported": 331,
"framework_architecture_unsupported": 335,
"memory_capacity": 11,
"model_load": 74,
"platform_infrastructure": 4,
"platform_infrastructure": 5,
"repository_structure": 8,
"runtime_memory": 6,
"tokenizer_compatibility": 50,
"tokenizer_compatibility": 51,
"参数/模板问题": 103,
"验证失败": 673
},
"failureCount": 1720,
"failureRate": 0.9668,
"failureCount": 1726,
"failureRate": 0.9669,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"platformFailureCount": 5,
"successCount": 59,
"successRate": 0.0332,
"total": 1779,
"successRate": 0.0331,
"total": 1785,
"unresolvedFailureCount": 1193
},
"warnings": [
@@ -7522,6 +7637,7 @@
"GPU Mthreads_s4000 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 Sunrise_pt-200-x1 本地统计失败率偏高≥50%),建议重点关注。",
"组合 Iluvatar_mrv-100|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Biren_166m|vllm|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|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -7544,6 +7660,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1866,
"summarizedRecords": 1878,
"version": 1
}

View File

@@ -14,13 +14,13 @@
100
],
"accounts": 12,
"activeScanned": 1000,
"activeScanned": 995,
"ageCleanupMode": "admission_only",
"agePolicySkipped": {
"cleanupDisabled": true,
"reason": "admission_only"
},
"architectureBlockCount": 74,
"architectureBlockCount": 75,
"architectureFrameworkCatalog": {
"ascend_910-b3|text-generation": [
"llamacpp",
@@ -32,21 +32,6 @@
"vllm",
"vllm_tokenizer_patch"
],
"biren_166m|text-generation": [
"vllm",
"vllm_fix_tokenizer",
"vllm_tokenizer_patch"
],
"cambricon_mlu-370-x4|text-generation": [
"vllm",
"vllm-customized",
"vllm-mlu"
],
"cambricon_mlu-370-x8|text-generation": [
"vllm",
"vllm-customized",
"vllm-mlu"
],
"hygon_k100-ai|text-generation": [
"llamacpp",
"vllm",
@@ -60,15 +45,6 @@
"vllm_fix_tokenizer",
"vllm_tokenizer_patch"
],
"iluvatar_mrv-100|text-generation": [
"transformers",
"vllm"
],
"kunlunxin_p-800|text-generation": [
"vllm",
"vllm_fix_tokenizer",
"vllm_tokenizer_patch"
],
"metax_c-500|text-generation": [
"vllm"
],
@@ -88,8 +64,135 @@
]
},
"architectureFrameworkCatalogErrors": {},
"architectureIncompatibleCount": 0,
"architectureIncompatibleTasks": [],
"architectureIncompatibleCount": 6,
"architectureIncompatibleTasks": [
{
"accountIndex": 1,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-13T21:05:21+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"evaluatedFrameworks": [
"vllm"
],
"framework": "vllm",
"gpuType": "Sunrise_pt-200-x1",
"modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4676625,
"taskType": "text-generation"
},
{
"accountIndex": 4,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-13T21:05:21+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"evaluatedFrameworks": [
"vllm"
],
"framework": "vllm",
"gpuType": "Sunrise_pt-200-x1",
"modelId": "groxaxo/qwen36-reap-2k-mlx-q8",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4679344,
"taskType": "text-generation"
},
{
"accountIndex": 5,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-13T21:05:21+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"evaluatedFrameworks": [
"vllm"
],
"framework": "vllm",
"gpuType": "Sunrise_pt-200-x1",
"modelId": "primitive-ai/Nex-N2.5-mini-NVFP4",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4761529,
"taskType": "text-generation"
},
{
"accountIndex": 6,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-13T21:05:21+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"evaluatedFrameworks": [
"vllm"
],
"framework": "vllm",
"gpuType": "Sunrise_pt-200-x1",
"modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4761528,
"taskType": "text-generation"
},
{
"accountIndex": 7,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-13T21:05:21+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"evaluatedFrameworks": [
"vllm"
],
"framework": "vllm",
"gpuType": "Sunrise_pt-200-x1",
"modelId": "primitive-ai/Nex-N2.5-mini-FP8",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4761532,
"taskType": "text-generation"
},
{
"accountIndex": 7,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-13T21:05:21+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"evaluatedFrameworks": [
"vllm"
],
"framework": "vllm",
"gpuType": "Sunrise_pt-200-x1",
"modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4804755,
"taskType": "text-generation"
}
],
"architectureModelConfigErrors": {
"GestaltLabs/Ornstein-3.5-9B-V2-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/GestaltLabs/Ornstein-3.5-9B-V2-GGUF/resolve/master/config.json (status=404)",
"LiquidAI/LFM2.5-2.6B-DSpark-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/LiquidAI/LFM2.5-2.6B-DSpark-GGUF/resolve/master/config.json (status=404)",
@@ -113,22 +216,167 @@
"z-lab/Qwen3.8-27B-DFlash2-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/z-lab/Qwen3.8-27B-DFlash2-GGUF/resolve/master/config.json (status=404)"
},
"architectureModelConfigsComplete": 93,
"architectureOnly": false,
"architectureOnly": true,
"architecturePolicySkipped": {
"frameworkCatalogUnknown": 0,
"frameworkContextUnknown": 271,
"frameworkCatalogUnknown": 66,
"frameworkContextUnknown": 269,
"modelArchitectureUnknown": 148,
"noMatchingBlock": 771,
"partiallyBlockedFrameworkSet": 81,
"noMatchingBlock": 693,
"partiallyBlockedFrameworkSet": 82,
"runningMatchedProtected": 0,
"submissionContextMismatch": 0,
"submissionContextUnknown": 0
},
"cancelledCount": 0,
"cancelledTasks": [],
"cancelledCount": 6,
"cancelledTasks": [
{
"accountIndex": 1,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-13T21:05:21+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"cleanupReasons": [
"known_framework_architecture_incompatible"
],
"evaluatedFrameworks": [
"vllm"
],
"framework": "vllm",
"gpuType": "Sunrise_pt-200-x1",
"modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4676625,
"taskType": "text-generation"
},
{
"accountIndex": 4,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-13T21:05:21+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"cleanupReasons": [
"known_framework_architecture_incompatible"
],
"evaluatedFrameworks": [
"vllm"
],
"framework": "vllm",
"gpuType": "Sunrise_pt-200-x1",
"modelId": "groxaxo/qwen36-reap-2k-mlx-q8",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4679344,
"taskType": "text-generation"
},
{
"accountIndex": 5,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-13T21:05:21+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"cleanupReasons": [
"known_framework_architecture_incompatible"
],
"evaluatedFrameworks": [
"vllm"
],
"framework": "vllm",
"gpuType": "Sunrise_pt-200-x1",
"modelId": "primitive-ai/Nex-N2.5-mini-NVFP4",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4761529,
"taskType": "text-generation"
},
{
"accountIndex": 6,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-13T21:05:21+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"cleanupReasons": [
"known_framework_architecture_incompatible"
],
"evaluatedFrameworks": [
"vllm"
],
"framework": "vllm",
"gpuType": "Sunrise_pt-200-x1",
"modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4761528,
"taskType": "text-generation"
},
{
"accountIndex": 7,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-13T21:05:21+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"cleanupReasons": [
"known_framework_architecture_incompatible"
],
"evaluatedFrameworks": [
"vllm"
],
"framework": "vllm",
"gpuType": "Sunrise_pt-200-x1",
"modelId": "primitive-ai/Nex-N2.5-mini-FP8",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4761532,
"taskType": "text-generation"
},
{
"accountIndex": 7,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-13T21:05:21+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"cleanupReasons": [
"known_framework_architecture_incompatible"
],
"evaluatedFrameworks": [
"vllm"
],
"framework": "vllm",
"gpuType": "Sunrise_pt-200-x1",
"modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4804755,
"taskType": "text-generation"
}
],
"certainOomCount": 0,
"certainOomTasks": [],
"cleanupCandidateCount": 0,
"cleanupCandidateCount": 6,
"dryRun": false,
"listingErrors": {},
"modelAgeErrors": {},
@@ -153,19 +401,17 @@
],
"oldOverflowCount": 0,
"oldOverflowTasks": [],
"policyCancelledRecorded": 0,
"policyCancelledRecorded": 6,
"policyNoLongerAppliesCount": 0,
"policyNoLongerAppliesTasks": [],
"recentModelDays": 7,
"recentModelReserveSlots": 5,
"repositorySizeErrors": {
"empero-ai/Qwen3.8-9B-GGUF": "recursive_repository_size_incomplete"
},
"repositorySizesComplete": 234,
"repositorySizeErrors": {},
"repositorySizesComplete": 0,
"skipped": {
"fitsKnownCapacity": 998,
"fitsKnownCapacity": 0,
"gpuCapacityUnknown": 0,
"repositorySizeUnknown": 2
"repositorySizeUnknown": 0
},
"stopErrors": [],
"uniqueModels": 235

View File

@@ -1,3 +1,7 @@
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["mellum"], "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-13T21:09:24.912761+00:00", "modelId": "JetBrains/Mellum2-12B-A2.5B-Instruct", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T21:09:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4152538", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "vllm", "lastSyncTime": "2026-09-13T21:09:24.912775+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T21:05:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4490277", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-13T21:09:24.912708+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T21:01:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4336358", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "platform_infrastructure", "failureAction": "open_short_gpu_framework_circuit_and_retry_other_models", "failureCategory": "platform_infrastructure", "failureClassificationReason": "no_idle_device", "failureCode": null, "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "gpu_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-13T21:09:24.912745+00:00", "modelId": "BAAI/AquilaMed-RL", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T21:01:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457974", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-13T19:32:14.039457+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T19:23:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4566587", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-13T16:43:44.912841+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T16:35:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523221", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["rwkv7"], "framework": "", "lastSyncTime": "2026-09-13T16:07:00.124635+00:00", "modelId": "RWKV/RWKV7-1.5B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T16:01:22+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4595685", "taskType": "text-generation", "verifyResult": -1}
@@ -294,7 +298,3 @@
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T18:09:45.834707+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T18:05:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471907", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["rwkv7"], "framework": "", "lastSyncTime": "2026-09-09T17:42:15.798661+00:00", "modelId": "RWKV/RWKV7-1.5B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T17:39:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610396", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-09T17:24:58.529030+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step240", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-09T17:23:22+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4458425", "taskType": "text-generation", "verifyResult": 1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T17:24:58.529069+00:00", "modelId": "neuralmagic/Mistral-7B-Instruct-v0.3-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T17:21:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4107009", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "platform_infrastructure", "failureAction": "open_short_gpu_framework_circuit_and_retry_other_models", "failureCategory": "platform_infrastructure", "failureClassificationReason": "no_idle_device", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "vllm", "lastSyncTime": "2026-09-09T17:24:58.529055+00:00", "modelId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T17:17:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4490281", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "", "lastSyncTime": "2026-09-09T16:50:57.940039+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T16:41:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610347", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-09T16:11:26.734386+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T16:05:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4477958", "taskType": "text-generation", "verifyResult": -1}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -175,7 +175,6 @@
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-7.2B-20260805", "modelId": "RWKV/RWKV7-7.2B-20260805", "submitTime": "2026-09-06T16:48:59.678173+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4672290", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-1.5B-20260805", "modelId": "RWKV/RWKV7-1.5B-20260805", "submitTime": "2026-09-06T18:34:36.628828+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4674757", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "submitTime": "2026-09-06T19:48:32.773868+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4676609", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "submitTime": "2026-09-06T19:48:32.797983+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4676625", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "submitTime": "2026-09-06T20:23:42.610808+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4677309", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenOneRec/OneReason-8B-pretrain-competition", "modelId": "OpenOneRec/OneReason-8B-pretrain-competition", "submitTime": "2026-09-06T20:54:07.883252+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4677960", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX", "modelId": "inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX", "submitTime": "2026-09-06T21:08:47.388697+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678359", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
@@ -184,7 +183,6 @@
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "submitTime": "2026-09-06T21:25:37.107095+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678756", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "submitTime": "2026-09-06T21:25:37.111002+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678760", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nota-ai/Nemotron-3.5-Lightning-30B-A3B-NVFP4-Global-Pruned-15", "modelId": "nota-ai/Nemotron-3.5-Lightning-30B-A3B-NVFP4-Global-Pruned-15", "submitTime": "2026-09-06T21:38:26.181785+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4679070", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/groxaxo/qwen36-reap-2k-mlx-q8", "modelId": "groxaxo/qwen36-reap-2k-mlx-q8", "submitTime": "2026-09-06T21:46:28.939188+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4679344", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B", "submitTime": "2026-09-06T21:55:23.563817+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4679536", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "submitTime": "2026-09-06T22:04:12.078346+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4679732", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/empero-ai/Qwen3.8-4B-Distill", "modelId": "empero-ai/Qwen3.8-4B-Distill", "submitTime": "2026-09-06T22:04:12.072657+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4679733", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
@@ -547,9 +545,6 @@
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "modelId": "CohereLabs/tiny-aya-en-thinker", "submitTime": "2026-09-10T13:27:23.410963+00:00", "targetGpu": "Biren_166m", "taskId": "4760705", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/laion/swesmith-nl2bash-stack-bugsseq", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "submitTime": "2026-09-10T13:27:23.404088+00:00", "targetGpu": "Biren_166m", "taskId": "4760700", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/BAAI/AREX-Turbo", "modelId": "BAAI/AREX-Turbo", "submitTime": "2026-09-10T13:27:23.409305+00:00", "targetGpu": "Biren_166m", "taskId": "4760704", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-NVFP4", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "submitTime": "2026-09-10T14:46:30.894640+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761529", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "submitTime": "2026-09-10T14:46:30.888510+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761528", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-FP8", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "submitTime": "2026-09-10T14:46:30.890611+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761532", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "modelId": "CohereLabs/tiny-aya-en-thinker", "submitTime": "2026-09-10T14:46:30.893195+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761530", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/BAAI/AREX-Turbo", "modelId": "BAAI/AREX-Turbo", "submitTime": "2026-09-10T14:46:30.895806+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761531", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/webAI-Official/TwIL-LM3", "modelId": "webAI-Official/TwIL-LM3", "submitTime": "2026-09-10T15:13:26.242352+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4761809", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-hygon-k100-ai"}
@@ -609,7 +604,6 @@
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.5-35B-A3B-8bit", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "submitTime": "2026-09-12T10:58:56.807180+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4800525", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B", "modelId": "unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B", "submitTime": "2026-09-12T10:58:56.798553+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4800526", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.5-35B-A3B-8bit", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "submitTime": "2026-09-12T14:09:52.635448+00:00", "targetGpu": "Biren_166m", "taskId": "4803464", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.5-35B-A3B-8bit", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "submitTime": "2026-09-12T16:07:22.080195+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4804755", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/cloudlnk/Spark-X2.5-4B-GGUF", "modelId": "cloudlnk/Spark-X2.5-4B-GGUF", "submitTime": "2026-09-12T16:59:17.247535+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4805292", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-hygon-k100-ai"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/cloudlnk/Spark-X2.5-4B-GGUF", "modelId": "cloudlnk/Spark-X2.5-4B-GGUF", "submitTime": "2026-09-12T17:16:39.306865+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4805471", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b3"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/cloudlnk/Spark-X2.5-4B-GGUF", "modelId": "cloudlnk/Spark-X2.5-4B-GGUF", "submitTime": "2026-09-12T17:35:57.210723+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4805660", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b4"}
@@ -629,6 +623,10 @@
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-INT8", "modelId": "XHToken/Spark-X2.5-4B-INT8", "submitTime": "2026-09-13T14:02:33.487789+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4829151", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-INT8", "modelId": "XHToken/Spark-X2.5-4B-INT8", "submitTime": "2026-09-13T14:24:08.911334+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4829350", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-INT8", "modelId": "XHToken/Spark-X2.5-4B-INT8", "submitTime": "2026-09-13T19:22:45.622511+00:00", "targetGpu": "Biren_166m", "taskId": "4834315", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-NVFP4", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "submitTime": "2026-09-10T14:46:30.894640+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761529", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "submitTime": "2026-09-10T14:46:30.888510+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761528", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-FP8", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "submitTime": "2026-09-10T14:46:30.890611+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761532", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.5-35B-A3B-8bit", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "submitTime": "2026-09-12T16:07:22.080195+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4804755", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "submitTime": "2026-09-08T16:07:42.654192+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4722475", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-2.9B-20260805", "modelId": "RWKV/RWKV7-2.9B-20260805", "submitTime": "2026-09-09T21:08:22.094532+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746447", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "submitTime": "2026-09-09T00:13:45.146237+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730594", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}

View File

@@ -1,24 +1,24 @@
{
"agentVersion": "2026.09.04.4",
"checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "f24b7e4b72d4b061f3e785842e75d7ac03e35c159173d8a429a9bcebd600bf68",
".modelhub_state/architecture_history_backfill.json": "9613157776b111868647d170acfbb17801724437ffaf30b64fe94bb7d5f05459",
".modelhub_state/market_intelligence.json": "d41e1ce2cb52df5cfe9d1323963ba9eeddb9bdf0d77d915a81eec39689f93fd1",
".modelhub_state/official_capabilities.json": "b52c4660c9e9a7ea915beb43d5d8efa41ea4a846c37a9b645050cc8d49fc2953",
".modelhub_state/outcome_checkpoint.json": "74c74711eeecb1c4d3864a7dc245863970ac690983d6861ca9ec6b62223d4b22",
".modelhub_state/queue_cleanup_latest.json": "f6b895b8233e19c5bd02b8861821ba25e5d8be5e7e5a8f29f659c01494c3199a",
".modelhub_state/recent_outcomes.jsonl": "62b659944f45c7254ddc38a7b6cc46a7faeab71e86fe611c2bf089c4a8bc96d0",
".modelhub_state/recovery_active_tasks.jsonl": "ccc39844acc4cc39385f64b758b4bf6f2f23a7c4580fba9501b26fee9f1f4250",
".modelhub_state/recovery_intents.jsonl": "0a70a4da87b124ad18dc970e4c7043f57aa1628a4cc880384078f72cba2a658a",
".modelhub_state/architecture_compatibility_blacklist.json": "7ad2645a9591bd21fb159ae04a5560e3b410b9e8ae8b15e86313e8723e30c291",
".modelhub_state/architecture_history_backfill.json": "23264edd723c6d916153eb19bd5c55d4d1006236472f4d608eb893e4b8ecfe10",
".modelhub_state/market_intelligence.json": "f7e60f5f868e4822395154c26df8f2216b0562c74190b78b076b25a62327884a",
".modelhub_state/official_capabilities.json": "e18df06efb177c38fce68c05ada066e37e112673274c53575ecabb6b58ca92e2",
".modelhub_state/outcome_checkpoint.json": "9cbbb13f206aef45fa0135e796ec08313b9e4cc981aa892aa315979a8aceda24",
".modelhub_state/queue_cleanup_latest.json": "5b70c9a058e6021cd29f839841baa8315fb09b5649608d2fb88bbcc940326138",
".modelhub_state/recent_outcomes.jsonl": "1e83aedcc2806d8d5ec1cec58b5ffb25ec57967182d378a5e788c295abcd4d2e",
".modelhub_state/recovery_active_tasks.jsonl": "c6799dc6693cd181b567a20b974a6287a4a118578a500f86b1351014528c61a1",
".modelhub_state/recovery_intents.jsonl": "e231a610f36858c26e3fa968ab6d014e5deb216fa0e2882457421a97ddd27a55",
".modelhub_state/routing_intelligence.json": "5a1ee27e192bc4bf70cd4d2daa949d5d751710cc5c0bbbd5862821ee6607cb9a",
".modelhub_state/submission_exclusions.jsonl": "75ddc8b4d313a8cecec2f373afc57298143d78e0eb907ca44f420d7bf9c55263",
".modelhub_state/worker_crashes.jsonl": "53505d335313446ff7094bcb58658b561de55799302fa7bfb49e418e414eebad",
"ledger/submissions.jsonl": "eac1b035667716d18b0cd4ea99139278314ca885285cf224c2188301ec9918cb",
"outcomes/submissions.jsonl": "990c40b70a88f527661fbfbb7d44ec57b4421669e8c96260c08f575467010411"
"ledger/submissions.jsonl": "bb967e6f6faeb151362b8c8457f7daa7521a81ea4d791fb97c2f5f1c6938eaa3",
"outcomes/submissions.jsonl": "deaaff755e3de1dde36f97900b11ecbe4e699f90413c7e62024c99014e137a80"
},
"generation": 6887,
"generation": 6888,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-13T21:08:24.245899+00:00",
"updatedAt": "2026-09-13T21:11:30.105455+00:00",
"writerId": "69701e73196b4ac2b3fad0f412335168"
}

View File

@@ -59,7 +59,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T00:58:33.712526+00:00", "modelId": "nm-testing/tinyllama-marlin24-w4a16-group128", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "382ef635ba042d77a729681df1994f5ac5e7beaf5980ac5d2e7045645d11c732", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 640856992, "estimatedRequiredGiB": 0.718, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 642705637, "modelscopeLicense": null, "modelscopeParams": 259844096, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 642705637}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T16:55:10.211615+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4630908", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T01:29:42.410346+00:00", "modelId": "pfnet/plamo-3-nict-8b-base", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16182734928, "estimatedRequiredGiB": 18.09, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 16186391993, "modelscopeLicense": "other", "modelscopeParams": 8091348992, "modelscopeTags": ["license:other", "model_type:plamo3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16186391993}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T17:27:00.623821+00:00", "targetGpu": "Biren_166m", "taskId": "4631345", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T02:08:42.512158+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 28168623119, "estimatedRequiredGiB": 31.505, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 28190535646, "modelscopeLicense": null, "modelscopeParams": 7584230528, "modelscopeTags": ["model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 28190535646}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T18:06:53.125751+00:00", "targetGpu": "Biren_166m", "taskId": "4631858", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T02:32:00.692516+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11998647728, "estimatedRequiredGiB": 13.434, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 12020564058, "modelscopeLicense": "gemma", "modelscopeParams": 10159209984, "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": 12020564058}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T18:26:10.985611+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4632116", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T02:32:00.692571+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23420419700, "estimatedRequiredGiB": 26.214, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23455515266, "modelscopeLicense": "mit", "modelscopeParams": 19528501104, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 23455515266}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T18:26:16.665549+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4632117", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T03:05:43.096396+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11998609696, "estimatedRequiredGiB": 13.434, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 12020499228, "modelscopeLicense": "gemma", "modelscopeParams": 10159209984, "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": 12020499228}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T19:03:47.678567+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4632579", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T03:32:15.596901+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4395007696, "estimatedRequiredGiB": 4.922, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 4404161088, "modelscopeLicense": "llama3.2", "modelscopeParams": 3606752256, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4404161088}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T19:29:42.987166+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4632974", "taskType": "text-generation", "verifyResult": null}
@@ -89,7 +88,6 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:04:40.397729+00:00", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3554214621, "estimatedRequiredGiB": 3.984, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://docs.mthreads.com/s4000/s4000-doc-online/product_specifications/"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 3564406686, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3564406686}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:03:09.000926+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4641564", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:04:40.397749+00:00", "modelId": "LLM-Research/Phi-3.5-mini-instruct-bnb-4bit", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2264298476, "estimatedRequiredGiB": 2.533, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2266692143, "modelscopeLicense": "mit", "modelscopeParams": 3934684872, "modelscopeTags": ["license:mit", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:unsloth", "custom_tag:transformers", "custom_tag:phi3", "custom_tag:phi", "custom_tag:microsoft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "bitsandbytes", "repositoryOnDiskBytes": 2266692143}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:03:09.034612+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4641566", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:20:02.142883+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-8bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9514532079, "estimatedRequiredGiB": 10.658, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:50"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9536343971, "modelscopeLicense": null, "modelscopeParams": 2519020032, "modelscopeTags": ["model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9536343971}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:17:16.436989+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4641789", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:20:02.142867+00:00", "modelId": "RWKV/RWKV7-2.9B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5896238160, "estimatedRequiredGiB": 6.592, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:50"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 5898265436, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2948065280, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5898265436}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:17:16.486519+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4641787", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:20:02.142903+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:50"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8842796317, "modelscopeLicense": "mit", "modelscopeParams": 6728625904, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 8842796317}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:17:16.435240+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4641790", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:20:02.142876+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8991501632, "estimatedRequiredGiB": 10.084, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:50"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9023443508, "modelscopeLicense": "mit", "modelscopeParams": 9409813744, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9023443508}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:17:16.439814+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4641788", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:20:02.142845+00:00", "modelId": "r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21921675140, "estimatedRequiredGiB": 24.525, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:50"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 21944922993, "modelscopeLicense": "apache-2.0", "modelscopeParams": 18589348592, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:vllm", "custom_tag:sm121", "custom_tag:gb10", "custom_tag:dgx-spark", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:modelopt"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 21944922993}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:17:16.438354+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4641791", "taskType": "text-generation", "verifyResult": null}
@@ -183,7 +181,6 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T00:59:44.608188+00:00", "modelId": "RWKV/RWKV7-7.2B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14399972864, "estimatedRequiredGiB": 16.095, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 14402000339, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7199932416, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 14402000339}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T16:48:59.678173+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4672290", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T02:37:59.437424+00:00", "modelId": "RWKV/RWKV7-1.5B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3055418240, "estimatedRequiredGiB": 3.417, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 3057371034, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1527668736, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3057371034}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T18:34:36.628828+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4674757", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T03:57:59.407871+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306310880, "estimatedRequiredGiB": 21.599, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19326449341, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9653104368, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:transformers", "custom_tag:unsloth", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:distillation", "custom_tag:deepseek", "custom_tag:sft", "custom_tag:rl", "custom_tag:gspo", "custom_tag:math", "custom_tag:stem", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:mtp"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19326449341}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T19:48:32.773868+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4676609", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T03:57:59.407808+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 28168623119, "estimatedRequiredGiB": 31.505, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 28190535646, "modelscopeLicense": null, "modelscopeParams": 7584230528, "modelscopeTags": ["model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 28190535646}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T19:48:32.797983+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4676625", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T04:34:12.697055+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29952487299, "estimatedRequiredGiB": 33.498, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 29973198172, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8027131120, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29973198172}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T20:23:42.610808+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4677309", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T05:05:30.903841+00:00", "modelId": "OpenOneRec/OneReason-8B-pretrain-competition", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16779959216, "estimatedRequiredGiB": 18.783, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": 8389956608, "modelscopeTags": ["model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:recommendation", "custom_tag:generative-recommendation", "custom_tag:reasoning", "custom_tag:itemic-token", "custom_tag:qwen3", "custom_tag:pretraining", "custom_tag:competition"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16806898419}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T20:54:07.883252+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4677960", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T05:18:43.228856+00:00", "modelId": "inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX", "modelProfile": {"architectures": [], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12994906286, "estimatedRequiredGiB": 14.53, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v4_dspark", "modelscopeFileSize": 13001289422, "modelscopeLicense": null, "modelscopeParams": 4276397927, "modelscopeTags": ["model_type:deepseek_v4_dspark", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13001289422}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T21:08:47.388697+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678359", "taskType": "text-generation", "verifyResult": null}
@@ -192,7 +189,6 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T05:31:35.012291+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {"architectures": ["NanbeigeForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5192364968, "estimatedRequiredGiB": 5.827, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanbeige", "modelscopeFileSize": 5214325469, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4169800704, "modelscopeTags": ["license:apache-2.0", "model_type:nanbeige", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5214325469}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T21:25:37.107095+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678756", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T05:31:35.012329+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8991501632, "estimatedRequiredGiB": 10.084, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9023443508, "modelscopeLicense": "mit", "modelscopeParams": 9409813744, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9023443508}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T21:25:37.111002+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678760", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T05:45:22.903446+00:00", "modelId": "nota-ai/Nemotron-3.5-Lightning-30B-A3B-NVFP4-Global-Pruned-15", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18974813860, "estimatedRequiredGiB": 21.229, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 18995666906, "modelscopeLicense": "other", "modelscopeParams": 15524066944, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 18995666906}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T21:38:26.181785+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4679070", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T06:07:37.711983+00:00", "modelId": "groxaxo/qwen36-reap-2k-mlx-q8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21551054131, "estimatedRequiredGiB": 24.108, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 21571271615, "modelscopeLicense": "other", "modelscopeParams": 6393958256, "modelscopeTags": ["license:other", "model_type:qwen3_5_moe", "library:mlx", "library:lora", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen3", "custom_tag:multimodal", "custom_tag:vision", "custom_tag:lora", "custom_tag:merged", "custom_tag:q8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21571271615}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T21:46:28.939188+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4679344", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T06:07:37.712071+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9319828096, "estimatedRequiredGiB": 10.438, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9339955920, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4659865088, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:transformers", "custom_tag:unsloth", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:distillation", "custom_tag:deepseek", "custom_tag:sft", "custom_tag:math", "custom_tag:stem", "custom_tag:mtp", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9339955920}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T21:55:23.563817+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4679536", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-07T06:07:37.712055+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T22:04:12.078346+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4679732", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-07T06:07:37.712005+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5777, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9342747188, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4659865088, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342747188}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T22:04:12.072657+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4679733", "taskType": "text-generation", "verifyResult": null}
@@ -556,9 +552,6 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T21:33:23.930703+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T13:27:23.410963+00:00", "targetGpu": "Biren_166m", "taskId": "4760705", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T21:33:23.930696+00:00", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16398873171, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T13:27:23.404088+00:00", "targetGpu": "Biren_166m", "taskId": "4760700", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T21:33:23.930655+00:00", "modelId": "BAAI/AREX-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9078620368, "estimatedRequiredGiB": 10.18, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9109259594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4539265536, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:deep-research", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:qwen3.5", "custom_tag:dense"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9109259594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T13:27:23.409305+00:00", "targetGpu": "Biren_166m", "taskId": "4760704", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T22:47:57.504477+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926484304, "estimatedRequiredGiB": 26.777, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23959625409, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107212656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23959625409}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T14:46:30.894640+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761529", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T22:47:57.504471+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26090095180, "modelscopeLicense": "apache-2.0", "modelscopeParams": 21416999792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:fp8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26090095180}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T14:46:30.888510+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761528", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T22:47:57.504443+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 38136526544, "estimatedRequiredGiB": 42.65, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 38162746086, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:fp8", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 38162746086}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T14:46:30.890611+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761532", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T22:47:57.504483+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T14:46:30.893195+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761530", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T22:47:57.504463+00:00", "modelId": "BAAI/AREX-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9078620368, "estimatedRequiredGiB": 10.18, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9109259594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4539265536, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:deep-research", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:qwen3.5", "custom_tag:dense"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9109259594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T14:46:30.895806+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761531", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-10T23:20:13.106498+00:00", "modelId": "webAI-Official/TwIL-LM3", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "e4ab8f6cadfae4845d02aa9c1f89de5907e1f311ae817b1e8e370b501bd7f2e9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3275575456, "estimatedRequiredGiB": 24.879, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 22261451378, "modelscopeLicense": "other", "modelscopeParams": 3075098624, "modelscopeTags": ["license:other", "model_type:smollm3", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:smollm3", "custom_tag:twil-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22261451381}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T15:13:26.242352+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4761809", "taskType": "text-generation", "verifyResult": null}
@@ -618,7 +611,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-12T18:59:53.316548+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37721402856, "estimatedRequiredGiB": 42.187, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 37748367893, "modelscopeLicense": "mit", "modelscopeParams": 10195701616, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-09T14:00:25.508497+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 37748367893}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T10:58:56.807180+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4800525", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-12T18:59:53.316560+00:00", "modelId": "unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 65827374264, "estimatedRequiredGiB": 73.588, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 65845719365, "modelscopeLicense": "other", "modelscopeParams": 32913266240, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 65845719365}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T10:58:56.798553+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4800526", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-12T22:16:38.428761+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37721402856, "estimatedRequiredGiB": 42.187, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 37748367893, "modelscopeLicense": "mit", "modelscopeParams": 10195701616, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37748367893}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T14:09:52.635448+00:00", "targetGpu": "Biren_166m", "taskId": "4803464", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-13T00:10:37.716551+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37721402856, "estimatedRequiredGiB": 42.187, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 37748367893, "modelscopeLicense": "mit", "modelscopeParams": 10195701616, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37748367893}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T16:07:22.080195+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4804755", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-13T01:02:56.601934+00:00", "modelId": "cloudlnk/Spark-X2.5-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "c21a8c5b2598ee6aec1301e1dba618e3f68c70a7ab35b6b215134aa6e6b9a3eb", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2405581632, "estimatedRequiredGiB": 17.589, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 15737975890, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark-x2.5", "custom_tag:long-context", "custom_tag:1m-context", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15737975890}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T16:59:17.247535+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4805292", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-13T01:20:19.415485+00:00", "modelId": "cloudlnk/Spark-X2.5-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "8a404c56481bc57c46ceeb762de172692775aca5bd1f8ef53c0e95ef96b93e6a", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2405581632, "estimatedRequiredGiB": 17.589, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 15737975890, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark-x2.5", "custom_tag:long-context", "custom_tag:1m-context", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15737975890}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T17:16:39.306865+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4805471", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-13T01:37:55.613775+00:00", "modelId": "cloudlnk/Spark-X2.5-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "29d7b6bec2440988a150b8d521c28df4707bcfe119f537490a5dfe23b9f8d11f", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2405581632, "estimatedRequiredGiB": 17.589, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 15737975890, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark-x2.5", "custom_tag:long-context", "custom_tag:1m-context", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15737975890}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T17:35:57.210723+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4805660", "taskType": "text-generation", "verifyResult": null}