state: generation 6534 (cycle)

This commit is contained in:
2026-09-13 05:05:05 +00:00
parent 7925f10c3d
commit 39de80f517
10 changed files with 2182 additions and 2136 deletions

View File

@@ -1454,7 +1454,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-13T05:02:22.759288+00:00",
"generatedAt": "2026-09-13T05:05:04.434325+00:00",
"summary": {
"activeBlockCount": 73,
"byGpuFramework": {

View File

@@ -35,7 +35,7 @@
"2": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 473,
"listingErrors": 474,
"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": 2,
"nextAccountIndex": 3,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-13T05:02:22.735825+00:00",
"updatedAt": "2026-09-13T05:05:04.410800+00:00",
"version": 1
}

View File

@@ -1,8 +1,8 @@
{
"communityAttemptedAt": "2026-09-13T04:47:27.365612+00:00",
"communityAttemptedAt": "2026-09-13T05:03:35.318656+00:00",
"communityError": null,
"communitySample": {},
"communityUpdatedAt": "2026-09-13T04:47:27.365612+00:00",
"communityUpdatedAt": "2026-09-13T05:03:35.318656+00:00",
"frameworkAttemptedAt": "2026-09-13T02:20:58.966988+00:00",
"frameworkError": null,
"frameworkStats": {
@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-13T05:00:28.999130+00:00",
"generatedAt": "2026-09-13T05:03:35.318656+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": "2026-09-13T04:31:31.956372+00:00",
"lastSyncTime": "2026-09-13T04:31:31.632761+00:00",
"generatedAt": "2026-09-13T05:03:24.000102+00:00",
"lastSyncTime": "2026-09-13T05:03:23.648984+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1740,11 +1740,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 19,
"ambiguous_runtime": 20,
"framework_architecture_unsupported": 7,
"参数/模板问题": 3
},
"failureCount": 29,
"failureCount": 30,
"failureRate": 1.0,
"framework": "vllm-mlu",
"pendingCount": 0,
@@ -1754,8 +1754,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 29,
"unresolvedFailureCount": 22
"total": 30,
"unresolvedFailureCount": 23
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 3,
@@ -2239,18 +2239,18 @@
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 4,
"attributableFailureCount": 5,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 1,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3,
"tokenizer_compatibility": 4,
"参数/模板问题": 2
},
"failureCount": 8,
"failureCount": 9,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2260,7 +2260,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 8,
"total": 9,
"unresolvedFailureCount": 3
},
"Vastai_va16|unknown|text-generation": {
@@ -2489,10 +2489,10 @@
"unresolvedFailureCount": 875
},
"vllm": {
"attributableFailureCount": 292,
"decisionFailureRate": 0.9898,
"decisionSuccessRate": 0.0102,
"decisionTotal": 295,
"attributableFailureCount": 293,
"decisionFailureRate": 0.9899,
"decisionSuccessRate": 0.0101,
"decisionTotal": 296,
"failureBreakdown": {
"ambiguous_runtime": 201,
"backend_operator": 34,
@@ -2502,17 +2502,17 @@
"platform_infrastructure": 1,
"repository_structure": 8,
"runtime_memory": 6,
"tokenizer_compatibility": 6,
"tokenizer_compatibility": 7,
"参数/模板问题": 24
},
"failureCount": 518,
"failureRate": 0.9942,
"failureCount": 519,
"failureRate": 0.9943,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0058,
"total": 521,
"successRate": 0.0057,
"total": 522,
"unresolvedFailureCount": 225
},
"vllm-mlu": {
@@ -2521,19 +2521,19 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 19,
"ambiguous_runtime": 20,
"framework_architecture_unsupported": 7,
"参数/模板问题": 3
},
"failureCount": 29,
"failureCount": 30,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 29,
"unresolvedFailureCount": 22
"total": 30,
"unresolvedFailureCount": 23
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 4,
@@ -2617,7 +2617,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-13T04:31:31.950508+00:00",
"generatedAt": "2026-09-13T05:03:23.994548+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 31,
@@ -2719,22 +2719,22 @@
"decisionSuccessRate": 0.1,
"decisionTotal": 20,
"failureBreakdown": {
"ambiguous_runtime": 39,
"ambiguous_runtime": 40,
"framework_architecture_unsupported": 16,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 18,
"验证失败": 22
},
"failureCount": 97,
"failureRate": 0.9798,
"failureCount": 98,
"failureRate": 0.98,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0202,
"total": 99,
"unresolvedFailureCount": 79
"successRate": 0.02,
"total": 100,
"unresolvedFailureCount": 80
},
"Iluvatar_bi-100": {
"attributableFailureCount": 0,
@@ -2877,27 +2877,27 @@
"unresolvedFailureCount": 77
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 50,
"decisionFailureRate": 0.9804,
"decisionSuccessRate": 0.0196,
"decisionTotal": 51,
"attributableFailureCount": 51,
"decisionFailureRate": 0.9808,
"decisionSuccessRate": 0.0192,
"decisionTotal": 52,
"failureBreakdown": {
"ambiguous_runtime": 1,
"backend_operator": 2,
"framework_architecture_unsupported": 5,
"platform_infrastructure": 3,
"tokenizer_compatibility": 43,
"tokenizer_compatibility": 44,
"参数/模板问题": 10,
"验证失败": 32
},
"failureCount": 96,
"failureRate": 0.9897,
"failureCount": 97,
"failureRate": 0.9898,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 1,
"successRate": 0.0103,
"total": 97,
"successRate": 0.0102,
"total": 98,
"unresolvedFailureCount": 43
},
"Vastai_va16": {
@@ -3287,6 +3287,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|spark2_5|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -4906,22 +4929,22 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 1,
"platform_infrastructure": 1,
"tokenizer_compatibility": 2
"tokenizer_compatibility": 3
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": "2026-09-09T17:17:21+00:00",
"lastTerminalAt": "2026-09-12T03:05:47.937901+00:00",
"lastTerminalAt": "2026-09-13T05:03:23.648954+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
@@ -4929,7 +4952,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 4,
"total": 5,
"unresolvedFailureCount": 1
},
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
@@ -5572,6 +5595,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|spark2_5|none|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 31,
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|starcoder2|compressed-tensors|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -7415,15 +7462,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1763,
"totalRecords": 1850,
"terminalRecords": 1765,
"totalRecords": 1852,
"totals": {
"attributableFailureCount": 510,
"decisionFailureRate": 0.8963,
"decisionSuccessRate": 0.1037,
"decisionTotal": 569,
"attributableFailureCount": 511,
"decisionFailureRate": 0.8965,
"decisionSuccessRate": 0.1035,
"decisionTotal": 570,
"failureBreakdown": {
"ambiguous_runtime": 414,
"ambiguous_runtime": 415,
"backend_operator": 43,
"framework_architecture_unsupported": 320,
"memory_capacity": 11,
@@ -7431,25 +7478,24 @@
"platform_infrastructure": 4,
"repository_structure": 8,
"runtime_memory": 6,
"tokenizer_compatibility": 49,
"tokenizer_compatibility": 50,
"参数/模板问题": 103,
"验证失败": 673
},
"failureCount": 1704,
"failureRate": 0.9665,
"failureCount": 1706,
"failureRate": 0.9666,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 59,
"successRate": 0.0335,
"total": 1763,
"unresolvedFailureCount": 1190
"successRate": 0.0334,
"total": 1765,
"unresolvedFailureCount": 1191
},
"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。",
@@ -7458,6 +7504,7 @@
"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。",
@@ -7480,6 +7527,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1850,
"summarizedRecords": 1852,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm", "lastSyncTime": "2026-09-13T05:03:23.648954+00:00", "modelId": "nm-testing/nonuniform", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T04:57:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4585193", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-13T04:23:07.613289+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T04:17:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4557614", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-13T04:05:56.910845+00:00", "modelId": "RedHatAI/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T04:05:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4332432", "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": "2026-09-13T04:05:56.910823+00:00", "modelId": "whcl412/mlx-LycheeAI-coder-1.7b", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T03:57:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4458813", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"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": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-09T11:08:33.010387+00:00", "modelId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T11:05:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4460755", "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": ["qwen3_5_mtp"], "framework": "", "lastSyncTime": "2026-09-09T11:01:57.287962+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-mxfp4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T11:01:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332978", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "", "lastSyncTime": "2026-09-09T10:14:08.904917+00:00", "modelId": "BAAI/AquilaMed-RL", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T10:11:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4421471", "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": "2026-09-09T09:03:44.512406+00:00", "modelId": "amd/Qwen3-4B-awq-quant-onnx-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T09:01:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079256", "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