state: generation 5317 (cycle)

This commit is contained in:
2026-09-10 19:00:46 +00:00
parent ae8411db2a
commit bc6574ca2b
10 changed files with 2205 additions and 2281 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T18:38:45.442913+00:00",
"lastSyncTime": "2026-09-10T18:38:45.206121+00:00",
"generatedAt": "2026-09-10T18:58:50.409136+00:00",
"lastSyncTime": "2026-09-10T18:58:50.012615+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1867,10 +1867,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 33,
"ambiguous_runtime": 34,
"参数/模板问题": 1
},
"failureCount": 34,
"failureCount": 35,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -1880,8 +1880,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 34,
"unresolvedFailureCount": 34
"total": 35,
"unresolvedFailureCount": 35
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2001,7 +2001,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 32,
"failureBreakdown": {
"ambiguous_runtime": 28,
"ambiguous_runtime": 33,
"backend_operator": 4,
"framework_architecture_unsupported": 22,
"memory_capacity": 1,
@@ -2010,7 +2010,7 @@
"runtime_memory": 2,
"参数/模板问题": 3
},
"failureCount": 63,
"failureCount": 68,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2020,8 +2020,8 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 63,
"unresolvedFailureCount": 31
"total": 68,
"unresolvedFailureCount": 36
},
"Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2323,7 +2323,7 @@
"decisionSuccessRate": 0.0083,
"decisionTotal": 242,
"failureBreakdown": {
"ambiguous_runtime": 178,
"ambiguous_runtime": 183,
"backend_operator": 33,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2334,15 +2334,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 24
},
"failureCount": 443,
"failureRate": 0.9955,
"failureCount": 448,
"failureRate": 0.9956,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 2,
"successRate": 0.0045,
"total": 445,
"unresolvedFailureCount": 202
"successRate": 0.0044,
"total": 450,
"unresolvedFailureCount": 207
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2409,22 +2409,22 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 38,
"failureBreakdown": {
"ambiguous_runtime": 35,
"ambiguous_runtime": 36,
"framework_architecture_unsupported": 4,
"model_load": 1,
"platform_infrastructure": 2,
"tokenizer_compatibility": 33,
"参数/模板问题": 7
},
"failureCount": 82,
"failureCount": 83,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 0,
"successRate": 0.0,
"total": 82,
"unresolvedFailureCount": 42
"total": 83,
"unresolvedFailureCount": 43
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 0,
@@ -2445,7 +2445,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T18:38:45.436829+00:00",
"generatedAt": "2026-09-10T18:58:50.404553+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2637,20 +2637,20 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 65,
"ambiguous_runtime": 66,
"memory_capacity": 1,
"参数/模板问题": 1,
"验证失败": 23
},
"failureCount": 90,
"failureCount": 91,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 90,
"unresolvedFailureCount": 89
"total": 91,
"unresolvedFailureCount": 90
},
"MetaX_c-500": {
"attributableFailureCount": 46,
@@ -2682,7 +2682,7 @@
"decisionSuccessRate": 0.0571,
"decisionTotal": 35,
"failureBreakdown": {
"ambiguous_runtime": 28,
"ambiguous_runtime": 33,
"backend_operator": 4,
"framework_architecture_unsupported": 22,
"memory_capacity": 1,
@@ -2692,15 +2692,15 @@
"参数/模板问题": 10,
"验证失败": 26
},
"failureCount": 97,
"failureRate": 0.9798,
"failureCount": 102,
"failureRate": 0.9808,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0202,
"total": 99,
"unresolvedFailureCount": 64
"successRate": 0.0192,
"total": 104,
"unresolvedFailureCount": 69
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 36,
@@ -3415,9 +3415,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
"ambiguous_runtime": 4
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5",
@@ -3429,8 +3429,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 4,
"unresolvedFailureCount": 4
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3|none": {
"attributableFailureCount": 0,
@@ -4172,11 +4172,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 13,
"ambiguous_runtime": 7,
"framework_architecture_unsupported": 4,
"参数/模板问题": 1
},
"failureCount": 18,
"failureCount": 12,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastPlatformFailureAt": null,
@@ -4188,8 +4188,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 18,
"unresolvedFailureCount": 14
"total": 12,
"unresolvedFailureCount": 8
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 3,
@@ -4330,13 +4330,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 18
"ambiguous_runtime": 19
},
"failureCount": 18,
"failureCount": 19,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T09:38:19.106782+00:00",
"lastTerminalAt": "2026-09-10T18:58:50.012615+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4344,8 +4344,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 18,
"unresolvedFailureCount": 18
"total": 19,
"unresolvedFailureCount": 19
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 6,
@@ -4406,16 +4406,16 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 8,
"ambiguous_runtime": 13,
"backend_operator": 3,
"framework_architecture_unsupported": 1,
"runtime_memory": 1
},
"failureCount": 13,
"failureCount": 18,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T16:54:17.206935+00:00",
"lastTerminalAt": "2026-09-10T18:58:50.012593+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4423,8 +4423,8 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 13,
"unresolvedFailureCount": 8
"total": 18,
"unresolvedFailureCount": 13
},
"Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -4659,81 +4659,6 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|phi3small|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastTerminalAt": "2026-09-08T18:40:55.416614+00:00",
"modelType": "phi3small",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"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|phi3|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastTerminalAt": "2026-09-08T20:25:19.301781+00:00",
"modelType": "phi3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen2|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastTerminalAt": "2026-09-08T20:58:55.412656+00:00",
"modelType": "qwen2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"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|qwen3_5_mtp|none": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
@@ -4791,9 +4716,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 5
"ambiguous_runtime": 3
},
"failureCount": 5,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastTerminalAt": "2026-09-08T16:13:44.313839+00:00",
@@ -4806,8 +4731,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 5
"total": 3,
"unresolvedFailureCount": 3
},
"Cambricon_mlu-370-x8|vllm|text-generation|qwen3_5_moe|eschamoe": {
"attributableFailureCount": 1,
@@ -5016,12 +4941,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-09T14:21:21.949441+00:00",
"lastTerminalAt": "2026-09-10T18:58:50.012615+00:00",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -5031,8 +4956,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|rwkv7|none": {
"attributableFailureCount": 0,
@@ -6171,9 +6096,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 33,
@@ -6186,8 +6111,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|none|34": {
"attributableFailureCount": 0,
@@ -7148,15 +7073,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1616,
"totalRecords": 1703,
"terminalRecords": 1622,
"totalRecords": 1709,
"totals": {
"attributableFailureCount": 421,
"decisionFailureRate": 0.8901,
"decisionSuccessRate": 0.1099,
"decisionTotal": 473,
"failureBreakdown": {
"ambiguous_runtime": 368,
"ambiguous_runtime": 374,
"backend_operator": 40,
"framework_architecture_unsupported": 272,
"memory_capacity": 11,
@@ -7168,31 +7093,30 @@
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1564,
"failureRate": 0.9678,
"failureCount": 1570,
"failureRate": 0.9679,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 52,
"successRate": 0.0322,
"total": 1616,
"unresolvedFailureCount": 1139
"successRate": 0.0321,
"total": 1622,
"unresolvedFailureCount": 1145
},
"warnings": [
"GPU Ascend_910-b3 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 Iluvatar_mrv-100 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 MetaX_c-500 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 Iluvatar_bi-150 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 Cambricon_mlu-370-x8 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-b4 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 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。",
"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。",
"组合 Cambricon_mlu-370-x4|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 Mthreads_s4000|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 Cambricon_mlu-370-x8|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 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -7207,10 +7131,11 @@
"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 Iluvatar_bi-150|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|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x4|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 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。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1703,
"summarizedRecords": 1709,
"version": 1
}