state: generation 8475 (cycle)

This commit is contained in:
2026-09-17 01:12:37 +00:00
parent 19eb32adc7
commit 2b143341b9
12 changed files with 2142 additions and 2371 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-17T00:53:22.021259+00:00",
"lastSyncTime": "2026-09-17T00:53:21.758627+00:00",
"generatedAt": "2026-09-17T01:10:41.663647+00:00",
"lastSyncTime": "2026-09-17T01:10:41.230667+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1086,6 +1086,25 @@
"targetGpu": "MetaX_c-500",
"taskType": "text-generation"
},
"mthreads_s4000|vllm|text-generation|model_type:gemma4": {
"architectureSignature": "model_type:gemma4",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-15T07:13:14.091353+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-15T07:13:14.091353+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "gemma4",
"sourceModelIds": [
"mlx-community/gemma-4-31B-it-qat-OptiQ-4bit"
],
"sourceTaskIds": [
"4868229"
],
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation"
},
"mthreads_s4000|vllm|text-generation|model_type:mellum": {
"architectureSignature": "model_type:mellum",
"architectures": [],
@@ -1721,7 +1740,7 @@
}
},
"architectureCompatibilitySummary": {
"activeBlockCount": 83,
"activeBlockCount": 84,
"byGpuFramework": {
"Ascend_910-b3|vllm": 11,
"Ascend_910-b3|vllm_tokenizer_patch": 1,
@@ -1730,7 +1749,7 @@
"Cambricon_mlu-370-x8|vllm-mlu": 5,
"Iluvatar_bi-150|vllm": 4,
"MetaX_c-500|vllm": 7,
"Mthreads_s4000|vllm": 8,
"Mthreads_s4000|vllm": 9,
"Sunrise_pt-200-x1|vllm": 3,
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 3,
"Vastai_va16|vllm": 15,
@@ -2388,30 +2407,30 @@
"unresolvedFailureCount": 58
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 58,
"decisionFailureRate": 0.8657,
"decisionSuccessRate": 0.1343,
"decisionTotal": 67,
"attributableFailureCount": 59,
"decisionFailureRate": 0.8676,
"decisionSuccessRate": 0.1324,
"decisionTotal": 68,
"failureBreakdown": {
"ambiguous_runtime": 11,
"backend_operator": 27,
"backend_operator": 28,
"framework_architecture_unsupported": 22,
"memory_capacity": 1,
"model_load": 7,
"repository_structure": 1,
"参数/模板问题": 9
},
"failureCount": 78,
"failureRate": 0.8966,
"failureCount": 79,
"failureRate": 0.8977,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 9,
"successRate": 0.1034,
"successRate": 0.1023,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 87,
"total": 88,
"unresolvedFailureCount": 20
},
"Mthreads_s4000|llamacpp|text-generation": {
@@ -2479,14 +2498,14 @@
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 42,
"decisionFailureRate": 0.875,
"decisionSuccessRate": 0.125,
"decisionTotal": 48,
"attributableFailureCount": 43,
"decisionFailureRate": 0.8776,
"decisionSuccessRate": 0.1224,
"decisionTotal": 49,
"failureBreakdown": {
"ambiguous_runtime": 42,
"ambiguous_runtime": 43,
"backend_operator": 4,
"framework_architecture_unsupported": 31,
"framework_architecture_unsupported": 32,
"memory_capacity": 1,
"model_load": 2,
"repository_structure": 1,
@@ -2494,18 +2513,18 @@
"tokenizer_compatibility": 1,
"参数/模板问题": 3
},
"failureCount": 87,
"failureRate": 0.9355,
"failureCount": 89,
"failureRate": 0.9368,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 6,
"successRate": 0.0645,
"successRate": 0.0632,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 93,
"unresolvedFailureCount": 45
"total": 95,
"unresolvedFailureCount": 46
},
"Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2723,14 +2742,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 55,
"failureBreakdown": {
"ambiguous_runtime": 22,
"ambiguous_runtime": 23,
"framework_architecture_unsupported": 43,
"memory_capacity": 1,
"model_load": 5,
"repository_structure": 4,
"runtime_memory": 2
},
"failureCount": 77,
"failureCount": 78,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2740,8 +2759,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 77,
"unresolvedFailureCount": 22
"total": 78,
"unresolvedFailureCount": 23
}
},
"frameworkSummaries": {
@@ -2810,14 +2829,14 @@
"unresolvedFailureCount": 904
},
"vllm": {
"attributableFailureCount": 380,
"decisionFailureRate": 0.9596,
"decisionSuccessRate": 0.0404,
"decisionTotal": 396,
"attributableFailureCount": 382,
"decisionFailureRate": 0.9598,
"decisionSuccessRate": 0.0402,
"decisionTotal": 398,
"failureBreakdown": {
"ambiguous_runtime": 222,
"backend_operator": 35,
"framework_architecture_unsupported": 284,
"ambiguous_runtime": 224,
"backend_operator": 36,
"framework_architecture_unsupported": 285,
"memory_capacity": 7,
"model_load": 31,
"platform_infrastructure": 2,
@@ -2826,15 +2845,15 @@
"tokenizer_compatibility": 9,
"参数/模板问题": 31
},
"failureCount": 635,
"failureRate": 0.9754,
"failureCount": 639,
"failureRate": 0.9756,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 16,
"successRate": 0.0246,
"total": 651,
"unresolvedFailureCount": 253
"successRate": 0.0244,
"total": 655,
"unresolvedFailureCount": 255
},
"vllm-mlu": {
"attributableFailureCount": 9,
@@ -2945,7 +2964,7 @@
"unresolvedFailureCount": 6
}
},
"generatedAt": "2026-09-17T00:53:22.014439+00:00",
"generatedAt": "2026-09-17T01:10:41.658007+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 51,
@@ -3158,13 +3177,13 @@
"unresolvedFailureCount": 125
},
"MetaX_c-500": {
"attributableFailureCount": 58,
"decisionFailureRate": 0.7632,
"decisionSuccessRate": 0.2368,
"decisionTotal": 76,
"attributableFailureCount": 59,
"decisionFailureRate": 0.7662,
"decisionSuccessRate": 0.2338,
"decisionTotal": 77,
"failureBreakdown": {
"ambiguous_runtime": 11,
"backend_operator": 27,
"backend_operator": 28,
"framework_architecture_unsupported": 22,
"memory_capacity": 1,
"model_load": 7,
@@ -3172,25 +3191,25 @@
"参数/模板问题": 19,
"验证失败": 48
},
"failureCount": 136,
"failureRate": 0.8831,
"failureCount": 137,
"failureRate": 0.8839,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 18,
"successRate": 0.1169,
"total": 154,
"successRate": 0.1161,
"total": 155,
"unresolvedFailureCount": 78
},
"Mthreads_s4000": {
"attributableFailureCount": 43,
"decisionFailureRate": 0.8431,
"decisionSuccessRate": 0.1569,
"decisionTotal": 51,
"attributableFailureCount": 44,
"decisionFailureRate": 0.8462,
"decisionSuccessRate": 0.1538,
"decisionTotal": 52,
"failureBreakdown": {
"ambiguous_runtime": 42,
"ambiguous_runtime": 43,
"backend_operator": 4,
"framework_architecture_unsupported": 31,
"framework_architecture_unsupported": 32,
"memory_capacity": 1,
"model_load": 3,
"repository_structure": 1,
@@ -3199,15 +3218,15 @@
"参数/模板问题": 11,
"验证失败": 26
},
"failureCount": 122,
"failureRate": 0.9385,
"failureCount": 124,
"failureRate": 0.9394,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 8,
"successRate": 0.0615,
"total": 130,
"unresolvedFailureCount": 79
"successRate": 0.0606,
"total": 132,
"unresolvedFailureCount": 80
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 66,
@@ -3263,7 +3282,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 62,
"failureBreakdown": {
"ambiguous_runtime": 27,
"ambiguous_runtime": 28,
"framework_architecture_unsupported": 49,
"memory_capacity": 1,
"model_load": 5,
@@ -3272,15 +3291,15 @@
"参数/模板问题": 10,
"验证失败": 27
},
"failureCount": 126,
"failureCount": 127,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 126,
"unresolvedFailureCount": 64
"total": 127,
"unresolvedFailureCount": 65
}
},
"observedGpuMemoryGiB": {
@@ -5618,6 +5637,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|gemma4|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "gemma4",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|glm_ocr|fp8": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -5687,6 +5729,29 @@
"total": 5,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|mistral3|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "mistral3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|nanbeige|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -6679,23 +6744,24 @@
"unresolvedFailureCount": 2
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"attributableFailureCount": 7,
"consecutiveFailures": 7,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 2,
"backend_operator": 1,
"framework_architecture_unsupported": 2,
"model_load": 3,
"repository_structure": 1
},
"failureCount": 8,
"failureCount": 9,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T21:39:57.012261+00:00",
"lastTerminalAt": "2026-09-17T01:10:41.230667+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -6703,7 +6769,7 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 8,
"total": 9,
"unresolvedFailureCount": 2
},
"Mthreads_s4000|unknown|text-generation": {
@@ -6732,18 +6798,18 @@
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 8,
"consecutiveFailures": 8,
"attributableFailureCount": 9,
"consecutiveFailures": 9,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 8,
"decisionTotal": 9,
"failureBreakdown": {
"ambiguous_runtime": 8,
"framework_architecture_unsupported": 7,
"ambiguous_runtime": 6,
"framework_architecture_unsupported": 8,
"tokenizer_compatibility": 1
},
"failureCount": 16,
"failureCount": 15,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -6755,8 +6821,8 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 16,
"unresolvedFailureCount": 8
"total": 15,
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -6917,22 +6983,22 @@
"unresolvedFailureCount": 2
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 15,
"consecutiveFailures": 15,
"attributableFailureCount": 14,
"consecutiveFailures": 14,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 15,
"decisionTotal": 14,
"failureBreakdown": {
"ambiguous_runtime": 5,
"framework_architecture_unsupported": 14,
"ambiguous_runtime": 6,
"framework_architecture_unsupported": 13,
"model_load": 1
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-17T00:44:27.123621+00:00",
"lastTerminalAt": "2026-09-17T01:10:41.230651+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -6941,7 +7007,7 @@
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 5
"unresolvedFailureCount": 6
}
},
"recentProfileCombinationStats": {
@@ -7020,6 +7086,56 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Mthreads_s4000|vllm|text-generation|gemma4|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-17T01:10:41.230600+00:00",
"modelType": "gemma4",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|mistral3|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-17T01:10:41.230625+00:00",
"modelType": "mistral3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -10613,6 +10729,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|gemma4|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "gemma4",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|glm_ocr|fp8|30": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -10707,6 +10847,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|mistral3|none|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "mistral3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|nanbeige|compressed-tensors|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -11425,17 +11589,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2065,
"totalRecords": 2168,
"terminalRecords": 2069,
"totalRecords": 2172,
"totals": {
"attributableFailureCount": 670,
"decisionFailureRate": 0.8874,
"decisionSuccessRate": 0.1126,
"decisionTotal": 755,
"attributableFailureCount": 672,
"decisionFailureRate": 0.8877,
"decisionSuccessRate": 0.1123,
"decisionTotal": 757,
"failureBreakdown": {
"ambiguous_runtime": 503,
"backend_operator": 45,
"framework_architecture_unsupported": 442,
"ambiguous_runtime": 505,
"backend_operator": 46,
"framework_architecture_unsupported": 443,
"memory_capacity": 12,
"model_load": 85,
"platform_infrastructure": 10,
@@ -11445,15 +11609,15 @@
"参数/模板问题": 124,
"验证失败": 673
},
"failureCount": 1980,
"failureRate": 0.9588,
"failureCount": 1984,
"failureRate": 0.9589,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 10,
"successCount": 85,
"successRate": 0.0412,
"total": 2065,
"unresolvedFailureCount": 1300
"successRate": 0.0411,
"total": 2069,
"unresolvedFailureCount": 1302
},
"warnings": [
"GPU Mthreads_s4000 本地统计失败率偏高≥50%),建议重点关注。",
@@ -11463,11 +11627,11 @@
"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 hygon_k100-ai 本地统计失败率偏高≥50%),建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Ascend_910-b3 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高≥50%),建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高≥50%),建议重点关注。",
"组合 Biren_166m|unknown|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 Vastai_va16|vllm_fix_tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -11492,6 +11656,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2168,
"summarizedRecords": 2172,
"version": 1
}