state: generation 5663 (cycle)

This commit is contained in:
2026-09-11 11:21:52 +00:00
parent 70fa3a5d2c
commit d1fbf0f264
9 changed files with 2164 additions and 2162 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-11T11:08:15.025709+00:00",
"lastSyncTime": "2026-09-11T11:08:14.809954+00:00",
"generatedAt": "2026-09-11T11:19:08.559808+00:00",
"lastSyncTime": "2026-09-11T11:19:08.306651+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2042,17 +2042,17 @@
"unresolvedFailureCount": 33
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 36,
"attributableFailureCount": 37,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 36,
"decisionTotal": 37,
"failureBreakdown": {
"framework_architecture_unsupported": 2,
"platform_infrastructure": 2,
"tokenizer_compatibility": 34,
"tokenizer_compatibility": 35,
"参数/模板问题": 6
},
"failureCount": 44,
"failureCount": 45,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -2062,21 +2062,22 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 44,
"total": 45,
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 1,
"platform_infrastructure": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 2
},
"failureCount": 5,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2086,7 +2087,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 5,
"total": 6,
"unresolvedFailureCount": 3
},
"Vastai_va16|unknown|text-generation": {
@@ -2315,10 +2316,10 @@
"unresolvedFailureCount": 858
},
"vllm": {
"attributableFailureCount": 240,
"attributableFailureCount": 241,
"decisionFailureRate": 0.9877,
"decisionSuccessRate": 0.0123,
"decisionTotal": 243,
"decisionTotal": 244,
"failureBreakdown": {
"ambiguous_runtime": 195,
"backend_operator": 33,
@@ -2328,17 +2329,17 @@
"platform_infrastructure": 1,
"repository_structure": 5,
"runtime_memory": 6,
"tokenizer_compatibility": 3,
"tokenizer_compatibility": 4,
"参数/模板问题": 24
},
"failureCount": 460,
"failureCount": 461,
"failureRate": 0.9935,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0065,
"total": 463,
"total": 464,
"unresolvedFailureCount": 219
},
"vllm-mlu": {
@@ -2401,26 +2402,26 @@
"unresolvedFailureCount": 4
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 39,
"attributableFailureCount": 40,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 39,
"decisionTotal": 40,
"failureBreakdown": {
"ambiguous_runtime": 36,
"framework_architecture_unsupported": 4,
"model_load": 1,
"platform_infrastructure": 2,
"tokenizer_compatibility": 34,
"tokenizer_compatibility": 35,
"参数/模板问题": 7
},
"failureCount": 84,
"failureCount": 85,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 0,
"successRate": 0.0,
"total": 84,
"total": 85,
"unresolvedFailureCount": 43
},
"vllm_tokenizer_patch": {
@@ -2442,7 +2443,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-11T11:08:15.021564+00:00",
"generatedAt": "2026-09-11T11:19:08.555805+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2700,26 +2701,26 @@
"unresolvedFailureCount": 77
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 37,
"decisionFailureRate": 0.9737,
"decisionSuccessRate": 0.0263,
"decisionTotal": 38,
"attributableFailureCount": 39,
"decisionFailureRate": 0.975,
"decisionSuccessRate": 0.025,
"decisionTotal": 40,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 3,
"platform_infrastructure": 3,
"tokenizer_compatibility": 34,
"tokenizer_compatibility": 36,
"参数/模板问题": 9,
"验证失败": 32
},
"failureCount": 82,
"failureRate": 0.988,
"failureCount": 84,
"failureRate": 0.9882,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 1,
"successRate": 0.012,
"total": 83,
"successRate": 0.0118,
"total": 85,
"unresolvedFailureCount": 42
},
"Vastai_va16": {
@@ -4415,22 +4416,22 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 15,
"consecutiveFailures": 15,
"attributableFailureCount": 16,
"consecutiveFailures": 16,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 15,
"decisionTotal": 16,
"failureBreakdown": {
"framework_architecture_unsupported": 1,
"platform_infrastructure": 2,
"tokenizer_compatibility": 14
"tokenizer_compatibility": 15
},
"failureCount": 17,
"failureCount": 18,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": "2026-09-10T11:01:21+00:00",
"lastTerminalAt": "2026-09-11T11:08:14.809954+00:00",
"lastTerminalAt": "2026-09-11T11:19:08.306628+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
@@ -4438,25 +4439,26 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 17,
"total": 18,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 1,
"platform_infrastructure": 1
"platform_infrastructure": 1,
"tokenizer_compatibility": 1
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": "2026-09-09T17:17:21+00:00",
"lastTerminalAt": "2026-09-10T12:06:09.109198+00:00",
"lastTerminalAt": "2026-09-11T11:19:08.306651+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
@@ -4464,7 +4466,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 1
},
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
@@ -6936,13 +6938,13 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1651,
"totalRecords": 1738,
"terminalRecords": 1653,
"totalRecords": 1740,
"totals": {
"attributableFailureCount": 431,
"decisionFailureRate": 0.8905,
"decisionSuccessRate": 0.1095,
"decisionTotal": 484,
"attributableFailureCount": 433,
"decisionFailureRate": 0.8909,
"decisionSuccessRate": 0.1091,
"decisionTotal": 486,
"failureBreakdown": {
"ambiguous_runtime": 391,
"backend_operator": 40,
@@ -6952,35 +6954,34 @@
"platform_infrastructure": 4,
"repository_structure": 5,
"runtime_memory": 6,
"tokenizer_compatibility": 40,
"tokenizer_compatibility": 42,
"参数/模板问题": 99,
"验证失败": 673
},
"failureCount": 1598,
"failureCount": 1600,
"failureRate": 0.9679,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 53,
"successRate": 0.0321,
"total": 1651,
"total": 1653,
"unresolvedFailureCount": 1163
},
"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。",
@@ -6995,10 +6996,11 @@
"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": 1738,
"summarizedRecords": 1740,
"version": 1
}