state: generation 8490 (cycle)

This commit is contained in:
2026-09-17 01:56:00 +00:00
parent 25228457f2
commit b4832645dd
9 changed files with 2034 additions and 1943 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-17T01:28:07.349913+00:00",
"lastSyncTime": "2026-09-17T01:28:07.114683+00:00",
"generatedAt": "2026-09-17T01:54:17.005156+00:00",
"lastSyncTime": "2026-09-17T01:54:16.705192+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1899,15 +1899,15 @@
"unresolvedFailureCount": 188
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
@@ -1917,7 +1917,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm|text-generation": {
@@ -2223,29 +2223,29 @@
"unresolvedFailureCount": 32
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
"attributableFailureCount": 23,
"decisionFailureRate": 0.8846,
"decisionSuccessRate": 0.1154,
"decisionTotal": 26,
"attributableFailureCount": 24,
"decisionFailureRate": 0.8889,
"decisionSuccessRate": 0.1111,
"decisionTotal": 27,
"failureBreakdown": {
"ambiguous_runtime": 12,
"backend_operator": 4,
"framework_architecture_unsupported": 6,
"framework_architecture_unsupported": 7,
"model_load": 4,
"runtime_memory": 9,
"参数/模板问题": 1
},
"failureCount": 36,
"failureRate": 0.9231,
"failureCount": 37,
"failureRate": 0.925,
"framework": "vllm_0_17_0_corex_4_4_0",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 3,
"successRate": 0.0769,
"successRate": 0.075,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 39,
"total": 40,
"unresolvedFailureCount": 13
},
"Iluvatar_bi-150|vllm|text-generation": {
@@ -2413,30 +2413,30 @@
"unresolvedFailureCount": 58
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 59,
"decisionFailureRate": 0.8676,
"decisionSuccessRate": 0.1324,
"decisionTotal": 68,
"attributableFailureCount": 60,
"decisionFailureRate": 0.8696,
"decisionSuccessRate": 0.1304,
"decisionTotal": 69,
"failureBreakdown": {
"ambiguous_runtime": 11,
"backend_operator": 28,
"backend_operator": 29,
"framework_architecture_unsupported": 22,
"memory_capacity": 1,
"model_load": 7,
"repository_structure": 1,
"参数/模板问题": 9
},
"failureCount": 79,
"failureRate": 0.8977,
"failureCount": 80,
"failureRate": 0.8989,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 9,
"successRate": 0.1023,
"successRate": 0.1011,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 88,
"total": 89,
"unresolvedFailureCount": 20
},
"Mthreads_s4000|llamacpp|text-generation": {
@@ -2835,13 +2835,13 @@
"unresolvedFailureCount": 904
},
"vllm": {
"attributableFailureCount": 385,
"decisionFailureRate": 0.9601,
"decisionSuccessRate": 0.0399,
"decisionTotal": 401,
"attributableFailureCount": 386,
"decisionFailureRate": 0.9602,
"decisionSuccessRate": 0.0398,
"decisionTotal": 402,
"failureBreakdown": {
"ambiguous_runtime": 225,
"backend_operator": 36,
"backend_operator": 37,
"framework_architecture_unsupported": 288,
"memory_capacity": 7,
"model_load": 31,
@@ -2851,14 +2851,14 @@
"tokenizer_compatibility": 9,
"参数/模板问题": 31
},
"failureCount": 643,
"failureRate": 0.9757,
"failureCount": 644,
"failureRate": 0.9758,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 16,
"successRate": 0.0243,
"total": 659,
"successRate": 0.0242,
"total": 660,
"unresolvedFailureCount": 256
},
"vllm-mlu": {
@@ -2904,26 +2904,26 @@
"unresolvedFailureCount": 11
},
"vllm_0_17_0_corex_4_4_0": {
"attributableFailureCount": 23,
"decisionFailureRate": 0.8846,
"decisionSuccessRate": 0.1154,
"decisionTotal": 26,
"attributableFailureCount": 24,
"decisionFailureRate": 0.8889,
"decisionSuccessRate": 0.1111,
"decisionTotal": 27,
"failureBreakdown": {
"ambiguous_runtime": 12,
"backend_operator": 4,
"framework_architecture_unsupported": 6,
"framework_architecture_unsupported": 7,
"model_load": 4,
"runtime_memory": 9,
"参数/模板问题": 1
},
"failureCount": 36,
"failureRate": 0.9231,
"failureCount": 37,
"failureRate": 0.925,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 3,
"successRate": 0.0769,
"total": 39,
"successRate": 0.075,
"total": 40,
"unresolvedFailureCount": 13
},
"vllm_fix_tokenizer": {
@@ -2951,26 +2951,26 @@
"unresolvedFailureCount": 69
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 6,
"attributableFailureCount": 7,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 6,
"framework_architecture_unsupported": 6
"framework_architecture_unsupported": 7
},
"failureCount": 12,
"failureCount": 13,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 12,
"total": 13,
"unresolvedFailureCount": 6
}
},
"generatedAt": "2026-09-17T01:28:07.344195+00:00",
"generatedAt": "2026-09-17T01:54:16.996577+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 51,
@@ -2996,13 +2996,13 @@
"unresolvedFailureCount": 73
},
"Ascend_910-b4": {
"attributableFailureCount": 59,
"decisionFailureRate": 0.9672,
"decisionSuccessRate": 0.0328,
"decisionTotal": 61,
"attributableFailureCount": 60,
"decisionFailureRate": 0.9677,
"decisionSuccessRate": 0.0323,
"decisionTotal": 62,
"failureBreakdown": {
"ambiguous_runtime": 43,
"framework_architecture_unsupported": 54,
"framework_architecture_unsupported": 55,
"memory_capacity": 1,
"model_load": 1,
"repository_structure": 1,
@@ -3010,14 +3010,14 @@
"参数/模板问题": 13,
"验证失败": 175
},
"failureCount": 290,
"failureCount": 291,
"failureRate": 0.9932,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0068,
"total": 292,
"total": 293,
"unresolvedFailureCount": 231
},
"Biren_166m": {
@@ -3112,28 +3112,28 @@
"unresolvedFailureCount": 29
},
"Iluvatar_bi-150": {
"attributableFailureCount": 50,
"decisionFailureRate": 0.8475,
"decisionSuccessRate": 0.1525,
"decisionTotal": 59,
"attributableFailureCount": 51,
"decisionFailureRate": 0.85,
"decisionSuccessRate": 0.15,
"decisionTotal": 60,
"failureBreakdown": {
"ambiguous_runtime": 20,
"backend_operator": 7,
"framework_architecture_unsupported": 20,
"framework_architecture_unsupported": 21,
"model_load": 11,
"repository_structure": 1,
"runtime_memory": 11,
"参数/模板问题": 3,
"验证失败": 30
},
"failureCount": 103,
"failureRate": 0.9196,
"failureCount": 104,
"failureRate": 0.9204,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 9,
"successRate": 0.0804,
"total": 112,
"successRate": 0.0796,
"total": 113,
"unresolvedFailureCount": 53
},
"Iluvatar_mrv-100": {
@@ -3183,13 +3183,13 @@
"unresolvedFailureCount": 126
},
"MetaX_c-500": {
"attributableFailureCount": 59,
"decisionFailureRate": 0.7662,
"decisionSuccessRate": 0.2338,
"decisionTotal": 77,
"attributableFailureCount": 60,
"decisionFailureRate": 0.7692,
"decisionSuccessRate": 0.2308,
"decisionTotal": 78,
"failureBreakdown": {
"ambiguous_runtime": 11,
"backend_operator": 28,
"backend_operator": 29,
"framework_architecture_unsupported": 22,
"memory_capacity": 1,
"model_load": 7,
@@ -3197,14 +3197,14 @@
"参数/模板问题": 19,
"验证失败": 48
},
"failureCount": 137,
"failureRate": 0.8839,
"failureCount": 138,
"failureRate": 0.8846,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 18,
"successRate": 0.1161,
"total": 155,
"successRate": 0.1154,
"total": 156,
"unresolvedFailureCount": 78
},
"Mthreads_s4000": {
@@ -3440,6 +3440,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_moe|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "qwen3_5_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|exl3": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -4657,6 +4680,29 @@
"total": 4,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|spark2_5|fp8": {
"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",
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "fp8",
"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": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -5393,15 +5439,15 @@
"unresolvedFailureCount": 1
},
"MetaX_c-500|vllm|text-generation|phi3|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 0.5,
"decisionSuccessRate": 0.5,
"decisionTotal": 2,
"attributableFailureCount": 2,
"decisionFailureRate": 0.6667,
"decisionSuccessRate": 0.3333,
"decisionTotal": 3,
"failureBreakdown": {
"backend_operator": 1
"backend_operator": 2
},
"failureCount": 1,
"failureRate": 0.5,
"failureCount": 2,
"failureRate": 0.6667,
"framework": "vllm",
"modelType": "phi3",
"pendingCount": 0,
@@ -5409,10 +5455,10 @@
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 1,
"successRate": 0.5,
"successRate": 0.3333,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|qwen2|none": {
@@ -7313,6 +7359,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_moe|compressed-tensors|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|exl3|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -9084,6 +9154,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|spark2_5|fp8|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": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "fp8",
"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,
@@ -10354,15 +10448,15 @@
"unresolvedFailureCount": 1
},
"MetaX_c-500|vllm|text-generation|phi3|compressed-tensors|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 0.5,
"decisionSuccessRate": 0.5,
"decisionTotal": 2,
"attributableFailureCount": 2,
"decisionFailureRate": 0.6667,
"decisionSuccessRate": 0.3333,
"decisionTotal": 3,
"failureBreakdown": {
"backend_operator": 1
"backend_operator": 2
},
"failureCount": 1,
"failureRate": 0.5,
"failureCount": 2,
"failureRate": 0.6667,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
"modelType": "phi3",
@@ -10371,10 +10465,10 @@
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 1,
"successRate": 0.5,
"successRate": 0.3333,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|qwen2|none|31": {
@@ -11667,17 +11761,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2074,
"totalRecords": 2177,
"terminalRecords": 2077,
"totalRecords": 2180,
"totals": {
"attributableFailureCount": 675,
"decisionFailureRate": 0.8882,
"decisionSuccessRate": 0.1118,
"decisionTotal": 760,
"attributableFailureCount": 678,
"decisionFailureRate": 0.8886,
"decisionSuccessRate": 0.1114,
"decisionTotal": 763,
"failureBreakdown": {
"ambiguous_runtime": 507,
"backend_operator": 46,
"framework_architecture_unsupported": 446,
"backend_operator": 47,
"framework_architecture_unsupported": 448,
"memory_capacity": 12,
"model_load": 85,
"platform_infrastructure": 10,
@@ -11687,14 +11781,14 @@
"参数/模板问题": 124,
"验证失败": 673
},
"failureCount": 1989,
"failureRate": 0.959,
"failureCount": 1992,
"failureRate": 0.9591,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 10,
"successCount": 85,
"successRate": 0.041,
"total": 2074,
"successRate": 0.0409,
"total": 2077,
"unresolvedFailureCount": 1304
},
"warnings": [
@@ -11705,11 +11799,11 @@
"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。",
@@ -11734,6 +11828,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2177,
"summarizedRecords": 2180,
"version": 1
}