state: generation 9679 (cycle)

This commit is contained in:
2026-09-19 06:24:11 +00:00
parent 1c6b8d0ce3
commit f7c00f04d0
10 changed files with 1927 additions and 1908 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-19T06:10:59.425068+00:00",
"lastSyncTime": "2026-09-19T06:10:59.181917+00:00",
"generatedAt": "2026-09-19T06:21:46.183691+00:00",
"lastSyncTime": "2026-09-19T06:21:46.148806+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2249,9 +2249,9 @@
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
"attributableFailureCount": 28,
"decisionFailureRate": 0.7,
"decisionSuccessRate": 0.3,
"decisionTotal": 40,
"decisionFailureRate": 0.6829,
"decisionSuccessRate": 0.3171,
"decisionTotal": 41,
"failureBreakdown": {
"ambiguous_runtime": 13,
"backend_operator": 4,
@@ -2261,16 +2261,16 @@
"参数/模板问题": 1
},
"failureCount": 42,
"failureRate": 0.7778,
"failureRate": 0.7636,
"framework": "vllm_0_17_0_corex_4_4_0",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 12,
"successRate": 0.2222,
"successCount": 13,
"successRate": 0.2364,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 54,
"total": 55,
"unresolvedFailureCount": 14
},
"Iluvatar_bi-150|vllm|text-generation": {
@@ -2531,9 +2531,9 @@
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 52,
"decisionFailureRate": 0.8,
"decisionSuccessRate": 0.2,
"decisionTotal": 65,
"decisionFailureRate": 0.7879,
"decisionSuccessRate": 0.2121,
"decisionTotal": 66,
"failureBreakdown": {
"ambiguous_runtime": 46,
"backend_operator": 6,
@@ -2546,16 +2546,16 @@
"参数/模板问题": 12
},
"failureCount": 110,
"failureRate": 0.8943,
"failureRate": 0.8871,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.1057,
"successCount": 14,
"successRate": 0.1129,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 123,
"total": 124,
"unresolvedFailureCount": 58
},
"Sunrise_pt-200-x1|unknown|text-generation": {
@@ -2863,9 +2863,9 @@
},
"vllm": {
"attributableFailureCount": 420,
"decisionFailureRate": 0.8861,
"decisionSuccessRate": 0.1139,
"decisionTotal": 474,
"decisionFailureRate": 0.8842,
"decisionSuccessRate": 0.1158,
"decisionTotal": 475,
"failureBreakdown": {
"ambiguous_runtime": 246,
"backend_operator": 40,
@@ -2879,13 +2879,13 @@
"参数/模板问题": 40
},
"failureCount": 708,
"failureRate": 0.9291,
"failureRate": 0.9279,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 54,
"successRate": 0.0709,
"total": 762,
"successCount": 55,
"successRate": 0.0721,
"total": 763,
"unresolvedFailureCount": 286
},
"vllm-mlu": {
@@ -2933,9 +2933,9 @@
},
"vllm_0_17_0_corex_4_4_0": {
"attributableFailureCount": 28,
"decisionFailureRate": 0.7,
"decisionSuccessRate": 0.3,
"decisionTotal": 40,
"decisionFailureRate": 0.6829,
"decisionSuccessRate": 0.3171,
"decisionTotal": 41,
"failureBreakdown": {
"ambiguous_runtime": 13,
"backend_operator": 4,
@@ -2945,13 +2945,13 @@
"参数/模板问题": 1
},
"failureCount": 42,
"failureRate": 0.7778,
"failureRate": 0.7636,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 12,
"successRate": 0.2222,
"total": 54,
"successCount": 13,
"successRate": 0.2364,
"total": 55,
"unresolvedFailureCount": 14
},
"vllm_fix_tokenizer": {
@@ -2998,7 +2998,7 @@
"unresolvedFailureCount": 18
}
},
"generatedAt": "2026-09-19T06:10:59.419691+00:00",
"generatedAt": "2026-09-19T06:21:46.178334+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 60,
@@ -3141,9 +3141,9 @@
},
"Iluvatar_bi-150": {
"attributableFailureCount": 55,
"decisionFailureRate": 0.7534,
"decisionSuccessRate": 0.2466,
"decisionTotal": 73,
"decisionFailureRate": 0.7432,
"decisionSuccessRate": 0.2568,
"decisionTotal": 74,
"failureBreakdown": {
"ambiguous_runtime": 21,
"backend_operator": 7,
@@ -3155,13 +3155,13 @@
"验证失败": 30
},
"failureCount": 109,
"failureRate": 0.8583,
"failureRate": 0.8516,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 18,
"successRate": 0.1417,
"total": 127,
"successCount": 19,
"successRate": 0.1484,
"total": 128,
"unresolvedFailureCount": 54
},
"Iluvatar_mrv-100": {
@@ -3237,9 +3237,9 @@
},
"Mthreads_s4000": {
"attributableFailureCount": 53,
"decisionFailureRate": 0.7794,
"decisionSuccessRate": 0.2206,
"decisionTotal": 68,
"decisionFailureRate": 0.7681,
"decisionSuccessRate": 0.2319,
"decisionTotal": 69,
"failureBreakdown": {
"ambiguous_runtime": 46,
"backend_operator": 6,
@@ -3253,13 +3253,13 @@
"验证失败": 26
},
"failureCount": 145,
"failureRate": 0.9062,
"failureRate": 0.9006,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 15,
"successRate": 0.0938,
"total": 160,
"successCount": 16,
"successRate": 0.0994,
"total": 161,
"unresolvedFailureCount": 92
},
"Sunrise_pt-200-x1": {
@@ -5008,25 +5008,25 @@
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|awq": {
"attributableFailureCount": 5,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"decisionFailureRate": 0.8333,
"decisionSuccessRate": 0.1667,
"decisionTotal": 6,
"failureBreakdown": {
"runtime_memory": 5
},
"failureCount": 5,
"failureRate": 1.0,
"failureRate": 0.8333,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"successCount": 1,
"successRate": 0.1667,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 5,
"total": 6,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|compressed-tensors": {
@@ -7006,7 +7006,7 @@
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 7,
"decisionTotal": 8,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
@@ -7016,11 +7016,11 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 7,
"successCount": 8,
"successRate": 1.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 7,
"total": 8,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|spark2_5|fp8": {
@@ -10824,6 +10824,28 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|awq|30": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 30,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|awq|32": {
"attributableFailureCount": 5,
"decisionFailureRate": 1.0,
@@ -14166,7 +14188,7 @@
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 6,
"decisionTotal": 7,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
@@ -14177,11 +14199,11 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 6,
"successCount": 7,
"successRate": 1.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 6,
"total": 7,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|qwen3|none|33": {
@@ -15217,13 +15239,13 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2302,
"totalRecords": 2405,
"terminalRecords": 2304,
"totalRecords": 2407,
"totals": {
"attributableFailureCount": 752,
"decisionFailureRate": 0.8319,
"decisionSuccessRate": 0.1681,
"decisionTotal": 904,
"decisionFailureRate": 0.83,
"decisionSuccessRate": 0.17,
"decisionTotal": 906,
"failureBreakdown": {
"ambiguous_runtime": 581,
"backend_operator": 55,
@@ -15238,17 +15260,17 @@
"验证失败": 673
},
"failureCount": 2150,
"failureRate": 0.934,
"failureRate": 0.9332,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 11,
"successCount": 152,
"successRate": 0.066,
"total": 2302,
"successCount": 154,
"successRate": 0.0668,
"total": 2304,
"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。",
@@ -15259,7 +15281,7 @@
"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。",
@@ -15284,6 +15306,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2405,
"summarizedRecords": 2407,
"version": 1
}