state: generation 9712 (cycle)

This commit is contained in:
2026-09-19 08:21:19 +00:00
parent 8b9283bb9f
commit acdfbed34e
9 changed files with 1893 additions and 1850 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-19T07:57:24.064448+00:00",
"lastSyncTime": "2026-09-19T07:57:23.789525+00:00",
"generatedAt": "2026-09-19T08:18:41.708825+00:00",
"lastSyncTime": "2026-09-19T08:18:41.447306+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1855,27 +1855,27 @@
"unresolvedFailureCount": 6
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 49,
"decisionFailureRate": 0.875,
"decisionSuccessRate": 0.125,
"decisionTotal": 56,
"attributableFailureCount": 50,
"decisionFailureRate": 0.8772,
"decisionSuccessRate": 0.1228,
"decisionTotal": 57,
"failureBreakdown": {
"ambiguous_runtime": 33,
"framework_architecture_unsupported": 47,
"framework_architecture_unsupported": 48,
"memory_capacity": 1,
"tokenizer_compatibility": 1
},
"failureCount": 82,
"failureRate": 0.9213,
"failureCount": 83,
"failureRate": 0.9222,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 7,
"successRate": 0.0787,
"successRate": 0.0778,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 89,
"total": 90,
"unresolvedFailureCount": 33
},
"Ascend_910-b4|llamacpp|text-generation": {
@@ -2048,24 +2048,24 @@
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation": {
"attributableFailureCount": 4,
"decisionFailureRate": 0.4,
"decisionSuccessRate": 0.6,
"decisionTotal": 10,
"decisionFailureRate": 0.3636,
"decisionSuccessRate": 0.6364,
"decisionTotal": 11,
"failureBreakdown": {
"ambiguous_runtime": 8,
"framework_architecture_unsupported": 4
},
"failureCount": 12,
"failureRate": 0.6667,
"failureRate": 0.6316,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 6,
"successRate": 0.3333,
"successCount": 7,
"successRate": 0.3684,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 18,
"total": 19,
"unresolvedFailureCount": 8
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
@@ -2249,9 +2249,9 @@
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
"attributableFailureCount": 28,
"decisionFailureRate": 0.6667,
"decisionSuccessRate": 0.3333,
"decisionTotal": 42,
"decisionFailureRate": 0.6512,
"decisionSuccessRate": 0.3488,
"decisionTotal": 43,
"failureBreakdown": {
"ambiguous_runtime": 13,
"backend_operator": 4,
@@ -2261,16 +2261,16 @@
"参数/模板问题": 1
},
"failureCount": 42,
"failureRate": 0.75,
"failureRate": 0.7368,
"framework": "vllm_0_17_0_corex_4_4_0",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 14,
"successRate": 0.25,
"successCount": 15,
"successRate": 0.2632,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 56,
"total": 57,
"unresolvedFailureCount": 14
},
"Iluvatar_bi-150|vllm|text-generation": {
@@ -2862,14 +2862,14 @@
"unresolvedFailureCount": 910
},
"vllm": {
"attributableFailureCount": 421,
"decisionFailureRate": 0.8845,
"decisionSuccessRate": 0.1155,
"decisionTotal": 476,
"attributableFailureCount": 422,
"decisionFailureRate": 0.8847,
"decisionSuccessRate": 0.1153,
"decisionTotal": 477,
"failureBreakdown": {
"ambiguous_runtime": 246,
"backend_operator": 40,
"framework_architecture_unsupported": 316,
"framework_architecture_unsupported": 317,
"memory_capacity": 7,
"model_load": 32,
"platform_infrastructure": 2,
@@ -2878,21 +2878,21 @@
"tokenizer_compatibility": 12,
"参数/模板问题": 40
},
"failureCount": 709,
"failureRate": 0.928,
"failureCount": 710,
"failureRate": 0.9281,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 55,
"successRate": 0.072,
"total": 764,
"successRate": 0.0719,
"total": 765,
"unresolvedFailureCount": 286
},
"vllm-mlu": {
"attributableFailureCount": 15,
"decisionFailureRate": 0.5172,
"decisionSuccessRate": 0.4828,
"decisionTotal": 29,
"decisionFailureRate": 0.5,
"decisionSuccessRate": 0.5,
"decisionTotal": 30,
"failureBreakdown": {
"ambiguous_runtime": 38,
"framework_architecture_unsupported": 14,
@@ -2900,13 +2900,13 @@
"参数/模板问题": 3
},
"failureCount": 56,
"failureRate": 0.8,
"failureRate": 0.7887,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 14,
"successRate": 0.2,
"total": 70,
"successCount": 15,
"successRate": 0.2113,
"total": 71,
"unresolvedFailureCount": 41
},
"vllm-patch-tokenizer": {
@@ -2933,9 +2933,9 @@
},
"vllm_0_17_0_corex_4_4_0": {
"attributableFailureCount": 28,
"decisionFailureRate": 0.6667,
"decisionSuccessRate": 0.3333,
"decisionTotal": 42,
"decisionFailureRate": 0.6512,
"decisionSuccessRate": 0.3488,
"decisionTotal": 43,
"failureBreakdown": {
"ambiguous_runtime": 13,
"backend_operator": 4,
@@ -2945,13 +2945,13 @@
"参数/模板问题": 1
},
"failureCount": 42,
"failureRate": 0.75,
"failureRate": 0.7368,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 14,
"successRate": 0.25,
"total": 56,
"successCount": 15,
"successRate": 0.2632,
"total": 57,
"unresolvedFailureCount": 14
},
"vllm_fix_tokenizer": {
@@ -2998,29 +2998,29 @@
"unresolvedFailureCount": 18
}
},
"generatedAt": "2026-09-19T07:57:24.059243+00:00",
"generatedAt": "2026-09-19T08:18:41.703239+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 61,
"decisionFailureRate": 0.8592,
"decisionSuccessRate": 0.1408,
"decisionTotal": 71,
"attributableFailureCount": 62,
"decisionFailureRate": 0.8611,
"decisionSuccessRate": 0.1389,
"decisionTotal": 72,
"failureBreakdown": {
"ambiguous_runtime": 39,
"framework_architecture_unsupported": 59,
"framework_architecture_unsupported": 60,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 10,
"验证失败": 27
},
"failureCount": 137,
"failureRate": 0.932,
"failureCount": 138,
"failureRate": 0.9324,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 10,
"successRate": 0.068,
"total": 147,
"successRate": 0.0676,
"total": 148,
"unresolvedFailureCount": 76
},
"Ascend_910-b4": {
@@ -3076,9 +3076,9 @@
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 34,
"decisionFailureRate": 0.7727,
"decisionSuccessRate": 0.2273,
"decisionTotal": 44,
"decisionFailureRate": 0.7556,
"decisionSuccessRate": 0.2444,
"decisionTotal": 45,
"failureBreakdown": {
"ambiguous_runtime": 47,
"framework_architecture_unsupported": 31,
@@ -3088,13 +3088,13 @@
"验证失败": 39
},
"failureCount": 121,
"failureRate": 0.9237,
"failureRate": 0.9167,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 10,
"successRate": 0.0763,
"total": 131,
"successCount": 11,
"successRate": 0.0833,
"total": 132,
"unresolvedFailureCount": 87
},
"Cambricon_mlu-370-x8": {
@@ -3141,9 +3141,9 @@
},
"Iluvatar_bi-150": {
"attributableFailureCount": 55,
"decisionFailureRate": 0.7333,
"decisionSuccessRate": 0.2667,
"decisionTotal": 75,
"decisionFailureRate": 0.7237,
"decisionSuccessRate": 0.2763,
"decisionTotal": 76,
"failureBreakdown": {
"ambiguous_runtime": 21,
"backend_operator": 7,
@@ -3155,13 +3155,13 @@
"验证失败": 30
},
"failureCount": 109,
"failureRate": 0.845,
"failureRate": 0.8385,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 20,
"successRate": 0.155,
"total": 129,
"successCount": 21,
"successRate": 0.1615,
"total": 130,
"unresolvedFailureCount": 54
},
"Iluvatar_mrv-100": {
@@ -3583,6 +3583,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm|text-generation|muse_glimmer|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm|text-generation|qwen3|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -4411,23 +4434,23 @@
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 6,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 0.1429,
"failureRate": 0.125,
"framework": "vllm-mlu",
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 6,
"successRate": 0.8571,
"successCount": 7,
"successRate": 0.875,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 7,
"total": 8,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|fp8": {
@@ -5077,25 +5100,25 @@
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 0.3333,
"decisionSuccessRate": 0.6667,
"decisionTotal": 3,
"decisionFailureRate": 0.25,
"decisionSuccessRate": 0.75,
"decisionTotal": 4,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 0.3333,
"failureRate": 0.25,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 2,
"successRate": 0.6667,
"successCount": 3,
"successRate": 0.75,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 3,
"total": 4,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|muse_glimmer|none": {
@@ -8935,6 +8958,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm|text-generation|muse_glimmer|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm|text-generation|qwen3|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -9989,12 +10036,12 @@
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 6,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 0.1429,
"failureRate": 0.125,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 32,
"modelType": "qwen3",
@@ -10002,11 +10049,11 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 6,
"successRate": 0.8571,
"successCount": 7,
"successRate": 0.875,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 7,
"total": 8,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|fp8|32": {
@@ -11039,7 +11086,7 @@
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
@@ -11050,11 +11097,11 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 2,
"successCount": 3,
"successRate": 1.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|muse_glimmer|none|34": {
@@ -15310,17 +15357,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2307,
"totalRecords": 2410,
"terminalRecords": 2310,
"totalRecords": 2413,
"totals": {
"attributableFailureCount": 754,
"decisionFailureRate": 0.8295,
"decisionSuccessRate": 0.1705,
"decisionTotal": 909,
"attributableFailureCount": 755,
"decisionFailureRate": 0.8279,
"decisionSuccessRate": 0.1721,
"decisionTotal": 912,
"failureBreakdown": {
"ambiguous_runtime": 581,
"backend_operator": 55,
"framework_architecture_unsupported": 505,
"framework_architecture_unsupported": 506,
"memory_capacity": 12,
"model_load": 88,
"platform_infrastructure": 11,
@@ -15330,18 +15377,18 @@
"参数/模板问题": 133,
"验证失败": 673
},
"failureCount": 2152,
"failureRate": 0.9328,
"failureCount": 2153,
"failureRate": 0.932,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 11,
"successCount": 155,
"successRate": 0.0672,
"total": 2307,
"successCount": 157,
"successRate": 0.068,
"total": 2310,
"unresolvedFailureCount": 1387
},
"warnings": [
"GPU Iluvatar_bi-150 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 Ascend_910-b3 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高(≥50%),建议重点关注。",
@@ -15352,7 +15399,7 @@
"GPU Sunrise_pt-200-x1 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。",
"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。",
"组合 MetaX_c-500|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_tokenizer_patch|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_mrv-100|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -15377,6 +15424,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2410,
"summarizedRecords": 2413,
"version": 1
}