state: generation 6250 (cycle)
This commit is contained in:
@@ -1383,7 +1383,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-12T15:07:41.589540+00:00",
|
||||
"generatedAt": "2026-09-12T15:10:28.378857+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 70,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -83,7 +83,7 @@
|
||||
"8": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 450,
|
||||
"listingErrors": 451,
|
||||
"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": 8,
|
||||
"nextAccountIndex": 9,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-12T15:07:41.565495+00:00",
|
||||
"updatedAt": "2026-09-12T15:10:28.354623+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-12T15:05:39.264649+00:00",
|
||||
"generatedAt": "2026-09-12T15:08:50.277851+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-12T14:41:33.654436+00:00",
|
||||
"lastSyncTime": "2026-09-12T14:41:33.434355+00:00",
|
||||
"generatedAt": "2026-09-12T15:08:42.536162+00:00",
|
||||
"lastSyncTime": "2026-09-12T15:08:42.332272+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1714,9 +1714,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 7
|
||||
"ambiguous_runtime": 8
|
||||
},
|
||||
"failureCount": 7,
|
||||
"failureCount": 8,
|
||||
"failureRate": 1.0,
|
||||
"framework": "transformers",
|
||||
"pendingCount": 0,
|
||||
@@ -1726,8 +1726,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 7,
|
||||
"unresolvedFailureCount": 7
|
||||
"total": 8,
|
||||
"unresolvedFailureCount": 8
|
||||
},
|
||||
"Iluvatar_bi-100|unknown|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -1816,26 +1816,26 @@
|
||||
"unresolvedFailureCount": 32
|
||||
},
|
||||
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
|
||||
"attributableFailureCount": 4,
|
||||
"decisionFailureRate": 0.6667,
|
||||
"decisionSuccessRate": 0.3333,
|
||||
"decisionTotal": 6,
|
||||
"attributableFailureCount": 5,
|
||||
"decisionFailureRate": 0.7143,
|
||||
"decisionSuccessRate": 0.2857,
|
||||
"decisionTotal": 7,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4,
|
||||
"backend_operator": 3,
|
||||
"framework_architecture_unsupported": 1
|
||||
"framework_architecture_unsupported": 2
|
||||
},
|
||||
"failureCount": 8,
|
||||
"failureRate": 0.8,
|
||||
"failureCount": 9,
|
||||
"failureRate": 0.8182,
|
||||
"framework": "vllm_0_17_0_corex_4_4_0",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.2,
|
||||
"successRate": 0.1818,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 10,
|
||||
"total": 11,
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"Iluvatar_bi-150|vllm|text-generation": {
|
||||
@@ -2378,17 +2378,17 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 7
|
||||
"ambiguous_runtime": 8
|
||||
},
|
||||
"failureCount": 7,
|
||||
"failureCount": 8,
|
||||
"failureRate": 1.0,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"total": 7,
|
||||
"unresolvedFailureCount": 7
|
||||
"total": 8,
|
||||
"unresolvedFailureCount": 8
|
||||
},
|
||||
"unknown": {
|
||||
"attributableFailureCount": 146,
|
||||
@@ -2483,23 +2483,23 @@
|
||||
"unresolvedFailureCount": 8
|
||||
},
|
||||
"vllm_0_17_0_corex_4_4_0": {
|
||||
"attributableFailureCount": 4,
|
||||
"decisionFailureRate": 0.6667,
|
||||
"decisionSuccessRate": 0.3333,
|
||||
"decisionTotal": 6,
|
||||
"attributableFailureCount": 5,
|
||||
"decisionFailureRate": 0.7143,
|
||||
"decisionSuccessRate": 0.2857,
|
||||
"decisionTotal": 7,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4,
|
||||
"backend_operator": 3,
|
||||
"framework_architecture_unsupported": 1
|
||||
"framework_architecture_unsupported": 2
|
||||
},
|
||||
"failureCount": 8,
|
||||
"failureRate": 0.8,
|
||||
"failureCount": 9,
|
||||
"failureRate": 0.8182,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.2,
|
||||
"total": 10,
|
||||
"successRate": 0.1818,
|
||||
"total": 11,
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"vllm_fix_tokenizer": {
|
||||
@@ -2545,7 +2545,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-12T14:41:33.648453+00:00",
|
||||
"generatedAt": "2026-09-12T15:08:42.531573+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 28,
|
||||
@@ -2670,42 +2670,42 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 8,
|
||||
"ambiguous_runtime": 9,
|
||||
"验证失败": 20
|
||||
},
|
||||
"failureCount": 28,
|
||||
"failureCount": 29,
|
||||
"failureRate": 1.0,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"total": 28,
|
||||
"unresolvedFailureCount": 28
|
||||
"total": 29,
|
||||
"unresolvedFailureCount": 29
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"attributableFailureCount": 30,
|
||||
"decisionFailureRate": 0.7895,
|
||||
"decisionSuccessRate": 0.2105,
|
||||
"decisionTotal": 38,
|
||||
"attributableFailureCount": 31,
|
||||
"decisionFailureRate": 0.7949,
|
||||
"decisionSuccessRate": 0.2051,
|
||||
"decisionTotal": 39,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 12,
|
||||
"backend_operator": 6,
|
||||
"framework_architecture_unsupported": 14,
|
||||
"framework_architecture_unsupported": 15,
|
||||
"model_load": 7,
|
||||
"repository_structure": 1,
|
||||
"runtime_memory": 2,
|
||||
"参数/模板问题": 2,
|
||||
"验证失败": 30
|
||||
},
|
||||
"failureCount": 74,
|
||||
"failureRate": 0.9024,
|
||||
"failureCount": 75,
|
||||
"failureRate": 0.9036,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 8,
|
||||
"successRate": 0.0976,
|
||||
"total": 82,
|
||||
"successRate": 0.0964,
|
||||
"total": 83,
|
||||
"unresolvedFailureCount": 44
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
@@ -3329,14 +3329,14 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|rwkv7|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"attributableFailureCount": 2,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
"framework_architecture_unsupported": 2
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_0_17_0_corex_4_4_0",
|
||||
"modelType": "rwkv7",
|
||||
@@ -3348,7 +3348,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|starcoder2|compressed-tensors": {
|
||||
@@ -4436,13 +4436,13 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2
|
||||
"ambiguous_runtime": 3
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "transformers",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-12T05:51:39.310788+00:00",
|
||||
"lastTerminalAt": "2026-09-12T15:08:42.332272+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4450,8 +4450,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Iluvatar_bi-150|unknown|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -4567,9 +4567,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 19
|
||||
"ambiguous_runtime": 18
|
||||
},
|
||||
"failureCount": 19,
|
||||
"failureCount": 18,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -4581,8 +4581,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 19,
|
||||
"unresolvedFailureCount": 19
|
||||
"total": 18,
|
||||
"unresolvedFailureCount": 18
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation": {
|
||||
"attributableFailureCount": 5,
|
||||
@@ -4880,9 +4880,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3
|
||||
"ambiguous_runtime": 2
|
||||
},
|
||||
"failureCount": 3,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastTerminalAt": "2026-09-09T11:33:22.442275+00:00",
|
||||
@@ -4895,8 +4895,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 3
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|phi3small|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -5841,6 +5841,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|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_0_17_0_corex_4_4_0",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
"modelType": "rwkv7",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|starcoder2|compressed-tensors|34": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -7256,17 +7280,17 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1723,
|
||||
"totalRecords": 1810,
|
||||
"terminalRecords": 1725,
|
||||
"totalRecords": 1812,
|
||||
"totals": {
|
||||
"attributableFailureCount": 484,
|
||||
"decisionFailureRate": 0.8946,
|
||||
"decisionSuccessRate": 0.1054,
|
||||
"decisionTotal": 541,
|
||||
"attributableFailureCount": 485,
|
||||
"decisionFailureRate": 0.8948,
|
||||
"decisionSuccessRate": 0.1052,
|
||||
"decisionTotal": 542,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 404,
|
||||
"ambiguous_runtime": 405,
|
||||
"backend_operator": 42,
|
||||
"framework_architecture_unsupported": 297,
|
||||
"framework_architecture_unsupported": 298,
|
||||
"memory_capacity": 11,
|
||||
"model_load": 72,
|
||||
"platform_infrastructure": 4,
|
||||
@@ -7276,20 +7300,21 @@
|
||||
"参数/模板问题": 101,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1666,
|
||||
"failureRate": 0.9669,
|
||||
"failureCount": 1668,
|
||||
"failureRate": 0.967,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 4,
|
||||
"successCount": 57,
|
||||
"successRate": 0.0331,
|
||||
"total": 1723,
|
||||
"unresolvedFailureCount": 1178
|
||||
"successRate": 0.033,
|
||||
"total": 1725,
|
||||
"unresolvedFailureCount": 1179
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Ascend_910-b3 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 Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
@@ -7298,7 +7323,6 @@
|
||||
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_bi-150 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 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 hygon_k100-ai|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 Ascend_910-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -7320,6 +7344,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1810,
|
||||
"summarizedRecords": 1812,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-12T15:08:42.332272+00:00", "modelId": "QuantTrio/KAT-Dev-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T15:01:21+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4079960", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-12T14:41:33.434355+00:00", "modelId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T14:35:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4543632", "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": ["nemotron_h"], "framework": "vllm", "lastSyncTime": "2026-09-12T14:12:46.256625+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T14:11:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4543480", "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": ["nemotron_h"], "framework": "vllm", "lastSyncTime": "2026-09-12T13:37:49.606306+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T13:37:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4546528", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -297,4 +298,3 @@
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T15:11:38.816901+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612468, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-07T06:07:37.712079+00:00", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 17788612468}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:51.818347+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729510", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T11:33:22.442275+00:00", "modelId": "nm-testing/Meta-llama3-8b-Instruct-SmoothQuant-Fp8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090490505, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-07T02:37:59.437448+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 9090490505}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:45.784701+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729501", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T14:42:07.646504+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test-bos", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090490459, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-07T02:37:59.437448+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 9090490459}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:45.697968+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729508", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T08:02:07.004675+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5700679600, "estimatedRequiredGiB": 6.381, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5709884743, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-07T02:37:59.437448+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 5709884743}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:45.685300+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729504", "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
@@ -1,24 +1,24 @@
|
||||
{
|
||||
"agentVersion": "2026.09.04.4",
|
||||
"checksums": {
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "74600d2efc065b3563b013b2b05e4739fdbfd874790cc5e81b07c25a55d23558",
|
||||
".modelhub_state/architecture_history_backfill.json": "f3297e9e682f2ea903cc737f778db61f724cc5ef0668a98195d67bc59996f235",
|
||||
".modelhub_state/market_intelligence.json": "e540463b9f9f0aca6f45fecf3a0a728ccaa7cc82e4a1561e81c0f4dd7082165d",
|
||||
".modelhub_state/official_capabilities.json": "68f23c37a78b364432e2b8779543fc3e3dfd82490f9e633c1eddc146aa26ab7a",
|
||||
".modelhub_state/outcome_checkpoint.json": "1456f673633f7b2e5db24836f5bb76ebf089a4bbf7005bd88499fea67b27c196",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "be781140983b4bb00a9163513ea7d4efd199fb4bf38f042c9de3893d72801df9",
|
||||
".modelhub_state/architecture_history_backfill.json": "a147d201a3a492329b7161afad01a9190723c9700fcaa9d487df9ec82bed0279",
|
||||
".modelhub_state/market_intelligence.json": "73c7514c218d60a9a5c505787283d47ae362d6061aa1533782056e5063ab1025",
|
||||
".modelhub_state/official_capabilities.json": "93d28473a9f83c6d95114e3c0b5e48126377930c80611611646b6326281061d6",
|
||||
".modelhub_state/outcome_checkpoint.json": "f10f8ea1c93b22740aa1a8da7e7a1328da8e845a2dd33d45714f016ffd268e1f",
|
||||
".modelhub_state/queue_cleanup_latest.json": "ecc68d43eaa771f35cd07fa219bd853d351a804602ed91e977e807e91d62ae63",
|
||||
".modelhub_state/recent_outcomes.jsonl": "d89360d9b1497793a7c0c0386ee9383eebd3c5264e9768b2c52a599dc109c7cb",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "a4484306fde8b1cd5e6074e888f756ad1e4b00add1f962f2343096a95d393cbc",
|
||||
".modelhub_state/recovery_intents.jsonl": "a04c98039a8d8673cf8b87ffe2d84cb41084845c0f4602ac0445556ebe2b765e",
|
||||
".modelhub_state/recent_outcomes.jsonl": "77088fd47d786b1d06c1dd07cc9f4659b7d7bb84564927af8e77e1e72be6b884",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "c86369526f14a31aea1bd8f49653276c3b8d1d5772f8059b367a29c991886d66",
|
||||
".modelhub_state/recovery_intents.jsonl": "acc60ea2fefd57c72762e4797d38c267c4db3324d7b8520085dd9c96eca3ff7a",
|
||||
".modelhub_state/routing_intelligence.json": "1fd08052d188703295b385ad2baefdf48051a8712c8c95922bacea9b34745263",
|
||||
".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220",
|
||||
".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162",
|
||||
"ledger/submissions.jsonl": "ca0794aeab385493f756235c9dd69be4eff4d8f005bdf57f93adf86b21bd571a",
|
||||
"outcomes/submissions.jsonl": "b3faebcefceff658cc7705ceb51ae1dfb110ecd9aa5991ba8c5d8a0add084858"
|
||||
"outcomes/submissions.jsonl": "86892e739e9a7a1426a694776f81507c5b8744626cdbe718255a011e32d01367"
|
||||
},
|
||||
"generation": 6249,
|
||||
"generation": 6250,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-12T15:07:41.679769+00:00",
|
||||
"updatedAt": "2026-09-12T15:10:29.191293+00:00",
|
||||
"writerId": "e5dd59a4c84a4f21926bad61448789e2"
|
||||
}
|
||||
|
||||
@@ -133,7 +133,6 @@
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T22:35:47.104165+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "99fcfb5673a881c74d82451063f2e7a90a328c33bce1e63a9d0bf3ccffd99170", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "modelscopeLicense": "other", "modelscopeParams": 327707521, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:speculative-decoding", "custom_tag:dspark", "custom_tag:lfm2", "custom_tag:draft-model", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T14:30:50.543106+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4650543", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T22:35:47.104188+00:00", "modelId": "callmezcc/Qwen3.8-27B-GPTQ-W4A16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19452784112, "estimatedRequiredGiB": 21.763, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19472982631, "modelscopeLicense": "openrail", "modelscopeParams": 27356728560, "modelscopeTags": ["license:openrail", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:4bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 19472982631}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T14:35:18.733791+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4650604", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T22:44:15.950234+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "05c5a771e8ede0f61c61c1696314e8cb295d87d07704eedc68e43f7483931e45", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "modelscopeLicense": "other", "modelscopeParams": 327707521, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:speculative-decoding", "custom_tag:dspark", "custom_tag:lfm2", "custom_tag:draft-model", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T14:39:36.525018+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4650654", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T22:44:15.950187+00:00", "modelId": "RWKV/RWKV7-2.9B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5896238160, "estimatedRequiredGiB": 6.592, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "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": "2026-09-05T14:43:25.822093+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4650705", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T23:08:33.934658+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {"architectures": ["NanbeigeForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5192364968, "estimatedRequiredGiB": 5.827, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-09-05T15:03:56.182791+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4650921", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T00:23:33.113639+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T16:20:38.385517+00:00", "targetGpu": "Vastai_va16", "taskId": "4651796", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T00:23:33.113688+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T16:20:38.391817+00:00", "targetGpu": "Vastai_va16", "taskId": "4651794", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user