state: generation 10035 (cycle)

This commit is contained in:
2026-09-19 23:16:40 +00:00
parent 2c2a064572
commit 94d0dbfd3f
10 changed files with 1893 additions and 1803 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-19T23:04:04.019390+00:00",
"lastSyncTime": "2026-09-19T23:04:02.598874+00:00",
"generatedAt": "2026-09-19T23:13:49.313762+00:00",
"lastSyncTime": "2026-09-19T23:13:47.695526+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2052,21 +2052,21 @@
"decisionSuccessRate": 0.5385,
"decisionTotal": 13,
"failureBreakdown": {
"ambiguous_runtime": 11,
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 6
},
"failureCount": 17,
"failureRate": 0.7083,
"failureCount": 18,
"failureRate": 0.72,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 7,
"successRate": 0.2917,
"successRate": 0.28,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 24,
"unresolvedFailureCount": 11
"total": 25,
"unresolvedFailureCount": 12
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 8,
@@ -2581,18 +2581,18 @@
"unresolvedFailureCount": 35
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 64,
"attributableFailureCount": 65,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 64,
"decisionTotal": 65,
"failureBreakdown": {
"backend_operator": 7,
"framework_architecture_unsupported": 7,
"platform_infrastructure": 8,
"tokenizer_compatibility": 50,
"tokenizer_compatibility": 51,
"参数/模板问题": 6
},
"failureCount": 78,
"failureCount": 79,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -2602,7 +2602,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 78,
"total": 79,
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -2655,26 +2655,26 @@
"unresolvedFailureCount": 145
},
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 6,
"decisionFailureRate": 0.8571,
"decisionSuccessRate": 0.1429,
"decisionTotal": 7,
"attributableFailureCount": 8,
"decisionFailureRate": 0.8889,
"decisionSuccessRate": 0.1111,
"decisionTotal": 9,
"failureBreakdown": {
"ambiguous_runtime": 9,
"framework_architecture_unsupported": 5,
"framework_architecture_unsupported": 7,
"model_load": 1
},
"failureCount": 15,
"failureRate": 0.9375,
"failureCount": 17,
"failureRate": 0.9444,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0625,
"successRate": 0.0556,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 16,
"total": 18,
"unresolvedFailureCount": 9
},
"Vastai_va16|vllm|text-generation": {
@@ -2683,12 +2683,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 62,
"failureBreakdown": {
"ambiguous_runtime": 76,
"ambiguous_runtime": 77,
"framework_architecture_unsupported": 56,
"memory_capacity": 1,
"model_load": 5
},
"failureCount": 138,
"failureCount": 139,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2698,8 +2698,8 @@
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 138,
"unresolvedFailureCount": 76
"total": 139,
"unresolvedFailureCount": 77
},
"hygon_k100-ai|llamacpp|text-generation": {
"attributableFailureCount": 0,
@@ -2867,7 +2867,7 @@
"decisionSuccessRate": 0.1386,
"decisionTotal": 498,
"failureBreakdown": {
"ambiguous_runtime": 247,
"ambiguous_runtime": 248,
"backend_operator": 40,
"framework_architecture_unsupported": 323,
"memory_capacity": 7,
@@ -2878,15 +2878,15 @@
"tokenizer_compatibility": 12,
"参数/模板问题": 40
},
"failureCount": 718,
"failureRate": 0.9123,
"failureCount": 719,
"failureRate": 0.9124,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 69,
"successRate": 0.0877,
"total": 787,
"unresolvedFailureCount": 287
"successRate": 0.0876,
"total": 788,
"unresolvedFailureCount": 288
},
"vllm-mlu": {
"attributableFailureCount": 18,
@@ -2894,20 +2894,20 @@
"decisionSuccessRate": 0.5,
"decisionTotal": 36,
"failureBreakdown": {
"ambiguous_runtime": 42,
"ambiguous_runtime": 43,
"framework_architecture_unsupported": 17,
"tokenizer_compatibility": 1,
"参数/模板问题": 3
},
"failureCount": 63,
"failureRate": 0.7778,
"failureCount": 64,
"failureRate": 0.7805,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 18,
"successRate": 0.2222,
"total": 81,
"unresolvedFailureCount": 45
"successRate": 0.2195,
"total": 82,
"unresolvedFailureCount": 46
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 17,
@@ -2955,27 +2955,27 @@
"unresolvedFailureCount": 14
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 70,
"decisionFailureRate": 0.9859,
"decisionSuccessRate": 0.0141,
"decisionTotal": 71,
"attributableFailureCount": 73,
"decisionFailureRate": 0.9865,
"decisionSuccessRate": 0.0135,
"decisionTotal": 74,
"failureBreakdown": {
"ambiguous_runtime": 85,
"backend_operator": 7,
"framework_architecture_unsupported": 12,
"framework_architecture_unsupported": 14,
"model_load": 1,
"platform_infrastructure": 8,
"tokenizer_compatibility": 50,
"tokenizer_compatibility": 51,
"参数/模板问题": 8
},
"failureCount": 171,
"failureRate": 0.9942,
"failureCount": 174,
"failureRate": 0.9943,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 8,
"successCount": 1,
"successRate": 0.0058,
"total": 172,
"successRate": 0.0057,
"total": 175,
"unresolvedFailureCount": 93
},
"vllm_tokenizer_patch": {
@@ -2998,7 +2998,7 @@
"unresolvedFailureCount": 22
}
},
"generatedAt": "2026-09-19T23:04:04.013701+00:00",
"generatedAt": "2026-09-19T23:13:49.307909+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 62,
@@ -3080,22 +3080,22 @@
"decisionSuccessRate": 0.234,
"decisionTotal": 47,
"failureBreakdown": {
"ambiguous_runtime": 50,
"ambiguous_runtime": 51,
"framework_architecture_unsupported": 33,
"memory_capacity": 1,
"tokenizer_compatibility": 2,
"参数/模板问题": 1,
"验证失败": 39
},
"failureCount": 126,
"failureRate": 0.9197,
"failureCount": 127,
"failureRate": 0.9203,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 11,
"successRate": 0.0803,
"total": 137,
"unresolvedFailureCount": 90
"successRate": 0.0797,
"total": 138,
"unresolvedFailureCount": 91
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 23,
@@ -3263,52 +3263,52 @@
"unresolvedFailureCount": 92
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 78,
"decisionFailureRate": 0.975,
"decisionSuccessRate": 0.025,
"decisionTotal": 80,
"attributableFailureCount": 79,
"decisionFailureRate": 0.9753,
"decisionSuccessRate": 0.0247,
"decisionTotal": 81,
"failureBreakdown": {
"ambiguous_runtime": 1,
"backend_operator": 8,
"framework_architecture_unsupported": 12,
"memory_capacity": 1,
"platform_infrastructure": 10,
"tokenizer_compatibility": 57,
"tokenizer_compatibility": 58,
"参数/模板问题": 18,
"验证失败": 32
},
"failureCount": 139,
"failureRate": 0.9858,
"failureCount": 140,
"failureRate": 0.9859,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 10,
"successCount": 2,
"successRate": 0.0142,
"total": 141,
"successRate": 0.0141,
"total": 142,
"unresolvedFailureCount": 51
},
"Vastai_va16": {
"attributableFailureCount": 68,
"decisionFailureRate": 0.7816,
"decisionSuccessRate": 0.2184,
"decisionTotal": 87,
"attributableFailureCount": 70,
"decisionFailureRate": 0.7865,
"decisionSuccessRate": 0.2135,
"decisionTotal": 89,
"failureBreakdown": {
"ambiguous_runtime": 85,
"framework_architecture_unsupported": 61,
"ambiguous_runtime": 86,
"framework_architecture_unsupported": 63,
"memory_capacity": 1,
"model_load": 6,
"参数/模板问题": 15,
"验证失败": 130
},
"failureCount": 298,
"failureRate": 0.9401,
"failureCount": 301,
"failureRate": 0.9406,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 19,
"successRate": 0.0599,
"total": 317,
"unresolvedFailureCount": 230
"successRate": 0.0594,
"total": 320,
"unresolvedFailureCount": 231
},
"hygon_k100-ai": {
"attributableFailureCount": 73,
@@ -4388,9 +4388,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 4
"ambiguous_runtime": 5
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "llama",
@@ -4402,8 +4402,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 4
"total": 5,
"unresolvedFailureCount": 5
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|muse_glimmer|none": {
"attributableFailureCount": 1,
@@ -7666,6 +7666,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Vastai_va16|vllm_fix_tokenizer|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_fix_tokenizer",
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -7689,6 +7712,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5|exl3": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "exl3",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5|modelopt": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -8305,9 +8351,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 1
},
"failureCount": 2,
"failureCount": 1,
"failureRate": 1.0,
"framework": "transformers",
"lastPlatformFailureAt": null,
@@ -8319,22 +8365,21 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"decisionTotal": 5,
"failureBreakdown": {
"backend_operator": 1,
"framework_architecture_unsupported": 4,
"model_load": 1
"framework_architecture_unsupported": 4
},
"failureCount": 6,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -8346,7 +8391,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 6,
"total": 5,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|unknown|text-generation": {
@@ -8561,22 +8606,22 @@
"unresolvedFailureCount": 2
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 10,
"consecutiveFailures": 10,
"attributableFailureCount": 11,
"consecutiveFailures": 11,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 10,
"decisionTotal": 11,
"failureBreakdown": {
"framework_architecture_unsupported": 3,
"platform_infrastructure": 4,
"tokenizer_compatibility": 7
"tokenizer_compatibility": 8
},
"failureCount": 14,
"failureCount": 15,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": "2026-09-16T02:03:21+00:00",
"lastTerminalAt": "2026-09-19T22:42:49.322287+00:00",
"lastTerminalAt": "2026-09-19T23:13:47.695526+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
@@ -8584,7 +8629,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 14,
"total": 15,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -8643,21 +8688,21 @@
"unresolvedFailureCount": 2
},
"Vastai_va16|vllm|text-generation": {
"attributableFailureCount": 8,
"consecutiveFailures": 8,
"attributableFailureCount": 7,
"consecutiveFailures": 7,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 8,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 8
"ambiguous_runtime": 13,
"framework_architecture_unsupported": 7
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-19T23:04:02.598845+00:00",
"lastTerminalAt": "2026-09-19T23:13:47.695492+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -8666,7 +8711,7 @@
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 12
"unresolvedFailureCount": 13
},
"hygon_k100-ai|llamacpp|text-generation": {
"attributableFailureCount": 0,
@@ -10383,9 +10428,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
"ambiguous_runtime": 4
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 32,
@@ -10398,8 +10443,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 4,
"unresolvedFailureCount": 4
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|muse_glimmer|none|34": {
"attributableFailureCount": 1,
@@ -15669,6 +15714,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Vastai_va16|vllm_fix_tokenizer|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_fix_tokenizer",
"loadSizeLog2Bucket": 34,
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -15693,6 +15762,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5|exl3|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "exl3",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5|modelopt|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -16201,38 +16294,38 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2363,
"totalRecords": 2466,
"terminalRecords": 2368,
"totalRecords": 2471,
"totals": {
"attributableFailureCount": 774,
"decisionFailureRate": 0.8147,
"decisionSuccessRate": 0.1853,
"decisionTotal": 950,
"attributableFailureCount": 777,
"decisionFailureRate": 0.8153,
"decisionSuccessRate": 0.1847,
"decisionTotal": 953,
"failureBreakdown": {
"ambiguous_runtime": 596,
"ambiguous_runtime": 598,
"backend_operator": 55,
"framework_architecture_unsupported": 520,
"framework_architecture_unsupported": 522,
"memory_capacity": 12,
"model_load": 89,
"platform_infrastructure": 11,
"repository_structure": 8,
"runtime_memory": 22,
"tokenizer_compatibility": 68,
"tokenizer_compatibility": 69,
"参数/模板问题": 133,
"验证失败": 673
},
"failureCount": 2187,
"failureRate": 0.9255,
"failureCount": 2192,
"failureRate": 0.9257,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 11,
"successCount": 176,
"successRate": 0.0745,
"total": 2363,
"unresolvedFailureCount": 1402
"successRate": 0.0743,
"total": 2368,
"unresolvedFailureCount": 1404
},
"warnings": [
"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 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。",
@@ -16243,7 +16336,7 @@
"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 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。",
"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。",
@@ -16268,6 +16361,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2466,
"summarizedRecords": 2471,
"version": 1
}