state: generation 11168 (cycle)

This commit is contained in:
2026-09-21 04:12:07 +00:00
parent e857d17891
commit 8598f7acc3
9 changed files with 1980 additions and 1939 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T04:08:31.325408+00:00",
"lastSyncTime": "2026-09-21T04:08:30.854649+00:00",
"generatedAt": "2026-09-21T04:11:58.039359+00:00",
"lastSyncTime": "2026-09-21T04:11:57.967213+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2406,7 +2406,7 @@
"vastai_va16|vllm|text-generation|model_type:qwen3_5": {
"architectureSignature": "model_type:qwen3_5",
"architectures": [],
"evidenceCount": 4,
"evidenceCount": 3,
"expiresAt": "2026-10-19T23:03:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-19T23:03:21+00:00",
@@ -2416,14 +2416,12 @@
"sourceModelIds": [
"Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B",
"r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121",
"ornith-ai/Ornith-1.5-9B-MLX-8bit",
"cyankiwi/Ornith-1.5-9B-AWQ-INT4"
"ornith-ai/Ornith-1.5-9B-MLX-8bit"
],
"sourceTaskIds": [
"4609086",
"4609094",
"4609081",
"4609101"
"4609081"
],
"targetGpu": "Vastai_va16",
"taskType": "text-generation"
@@ -2585,22 +2583,22 @@
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 1,
"参数/模板问题": 19,
"参数/模板问题": 20,
"日志缺失": 2,
"验证失败": 26
},
"failureCount": 48,
"failureRate": 0.8889,
"failureCount": 49,
"failureRate": 0.8909,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 6,
"successRate": 0.1111,
"successRate": 0.1091,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 54,
"unresolvedFailureCount": 48
"total": 55,
"unresolvedFailureCount": 49
},
"Ascend_910-b3|unknown|visual-multi-modal": {
"attributableFailureCount": 0,
@@ -4472,9 +4470,9 @@
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 67,
"decisionFailureRate": 0.7701,
"decisionSuccessRate": 0.2299,
"decisionTotal": 87,
"decisionFailureRate": 0.7614,
"decisionSuccessRate": 0.2386,
"decisionTotal": 88,
"failureBreakdown": {
"ambiguous_runtime": 61,
"backend_operator": 8,
@@ -4487,16 +4485,16 @@
"参数/模板问题": 12
},
"failureCount": 140,
"failureRate": 0.875,
"failureRate": 0.8696,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 20,
"successRate": 0.125,
"successCount": 21,
"successRate": 0.1304,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 160,
"total": 161,
"unresolvedFailureCount": 73
},
"Mthreads_s4000|vllm|visual-multi-modal": {
@@ -4543,9 +4541,9 @@
},
"Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 13,
"decisionFailureRate": 0.1287,
"decisionSuccessRate": 0.8713,
"decisionTotal": 101,
"decisionFailureRate": 0.1275,
"decisionSuccessRate": 0.8725,
"decisionTotal": 102,
"failureBreakdown": {
"ambiguous_runtime": 52,
"context_length": 5,
@@ -4554,16 +4552,16 @@
"验证失败": 32
},
"failureCount": 309,
"failureRate": 0.7783,
"failureRate": 0.7764,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 88,
"successRate": 0.2217,
"successCount": 89,
"successRate": 0.2236,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 397,
"total": 398,
"unresolvedFailureCount": 296
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
@@ -5088,9 +5086,9 @@
},
"unknown": {
"attributableFailureCount": 1858,
"decisionFailureRate": 0.6967,
"decisionSuccessRate": 0.3033,
"decisionTotal": 2667,
"decisionFailureRate": 0.6964,
"decisionSuccessRate": 0.3036,
"decisionTotal": 2668,
"failureBreakdown": {
"ambiguous_runtime": 1964,
"architecture_compatibility": 100,
@@ -5103,25 +5101,25 @@
"repository_structure": 264,
"runtime_memory": 3,
"tokenizer_compatibility": 157,
"参数/模板问题": 3059,
"参数/模板问题": 3060,
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 8315,
"failureRate": 0.9113,
"failureCount": 8316,
"failureRate": 0.9112,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 42,
"successCount": 809,
"successRate": 0.0887,
"total": 9124,
"unresolvedFailureCount": 6415
"successCount": 810,
"successRate": 0.0888,
"total": 9126,
"unresolvedFailureCount": 6416
},
"vllm": {
"attributableFailureCount": 3506,
"decisionFailureRate": 0.9769,
"decisionSuccessRate": 0.0231,
"decisionTotal": 3589,
"decisionFailureRate": 0.9766,
"decisionSuccessRate": 0.0234,
"decisionTotal": 3590,
"failureBreakdown": {
"ambiguous_runtime": 1463,
"architecture_compatibility": 112,
@@ -5138,13 +5136,13 @@
"参数/模板问题": 41
},
"failureCount": 5874,
"failureRate": 0.9861,
"failureRate": 0.9859,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 864,
"successCount": 83,
"successRate": 0.0139,
"total": 5957,
"successCount": 84,
"successRate": 0.0141,
"total": 5958,
"unresolvedFailureCount": 1504
},
"vllm-customized": {
@@ -5283,7 +5281,7 @@
"unresolvedFailureCount": 64
}
},
"generatedAt": "2026-09-21T04:08:31.315024+00:00",
"generatedAt": "2026-09-21T04:11:58.028763+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 90,
@@ -5296,19 +5294,19 @@
"memory_capacity": 2,
"repository_structure": 1,
"tokenizer_compatibility": 2,
"参数/模板问题": 27,
"参数/模板问题": 28,
"日志缺失": 3,
"验证失败": 27
},
"failureCount": 221,
"failureRate": 0.9208,
"failureCount": 222,
"failureRate": 0.9212,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 19,
"successRate": 0.0792,
"total": 240,
"unresolvedFailureCount": 131
"successRate": 0.0788,
"total": 241,
"unresolvedFailureCount": 132
},
"Ascend_910-b4": {
"attributableFailureCount": 313,
@@ -5581,9 +5579,9 @@
},
"Mthreads_s4000": {
"attributableFailureCount": 71,
"decisionFailureRate": 0.6396,
"decisionSuccessRate": 0.3604,
"decisionTotal": 111,
"decisionFailureRate": 0.6339,
"decisionSuccessRate": 0.3661,
"decisionTotal": 112,
"failureBreakdown": {
"ambiguous_runtime": 107,
"backend_operator": 8,
@@ -5598,20 +5596,20 @@
"验证失败": 26
},
"failureCount": 356,
"failureRate": 0.899,
"failureRate": 0.8967,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 40,
"successRate": 0.101,
"total": 396,
"successCount": 41,
"successRate": 0.1033,
"total": 397,
"unresolvedFailureCount": 285
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 732,
"decisionFailureRate": 0.8927,
"decisionSuccessRate": 0.1073,
"decisionTotal": 820,
"decisionFailureRate": 0.8916,
"decisionSuccessRate": 0.1084,
"decisionTotal": 821,
"failureBreakdown": {
"ambiguous_runtime": 162,
"architecture_compatibility": 44,
@@ -5627,13 +5625,13 @@
"验证失败": 32
},
"failureCount": 1372,
"failureRate": 0.9397,
"failureRate": 0.9391,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 218,
"successCount": 88,
"successRate": 0.0603,
"total": 1460,
"successCount": 89,
"successRate": 0.0609,
"total": 1461,
"unresolvedFailureCount": 422
},
"Vastai_va16": {
@@ -12775,23 +12773,23 @@
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 4,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 0.2,
"failureRate": 0.1667,
"framework": "vllm",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 4,
"successRate": 0.8,
"successCount": 5,
"successRate": 0.8333,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 5,
"total": 6,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|mistral3|none": {
@@ -14023,13 +14021,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 1,
"参数/模板问题": 1
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-20T17:39:36.352421+00:00",
"lastTerminalAt": "2026-09-21T04:11:57.967175+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -14037,8 +14036,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 9,
@@ -14668,28 +14667,27 @@
"unresolvedFailureCount": 5
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"attributableFailureCount": 4,
"consecutiveFailures": 2,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionFailureRate": 0.8,
"decisionSuccessRate": 0.2,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 4,
"backend_operator": 1,
"framework_architecture_unsupported": 3,
"runtime_memory": 1
},
"failureCount": 9,
"failureRate": 1.0,
"failureCount": 8,
"failureRate": 0.8889,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-20T22:20:31.465723+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"successCount": 1,
"successRate": 0.1111,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 9,
@@ -14701,21 +14699,21 @@
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 4,
"decisionTotal": 5,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T03:09:23.977124+00:00",
"lastTerminalAt": "2026-09-21T04:11:57.967213+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 4,
"successCount": 5,
"successRate": 1.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 4,
"total": 5,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
@@ -14769,17 +14767,17 @@
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm|text-generation": {
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 10,
"framework_architecture_unsupported": 5
"ambiguous_runtime": 9,
"framework_architecture_unsupported": 4
},
"failureCount": 15,
"failureCount": 13,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -14791,8 +14789,8 @@
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 15,
"unresolvedFailureCount": 10
"total": 13,
"unresolvedFailureCount": 9
},
"hygon_k100-ai|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -18557,6 +18555,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|llama|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-21T04:11:57.967192+00:00",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|sophia_hybrid|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -29117,6 +29138,28 @@
"total": 4,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|llama|none|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|mistral3|none|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -30837,13 +30880,13 @@
"unresolvedFailureCount": 1
}
},
"terminalRecords": 16079,
"totalRecords": 16257,
"terminalRecords": 16082,
"totalRecords": 16260,
"totals": {
"attributableFailureCount": 5839,
"decisionFailureRate": 0.8617,
"decisionSuccessRate": 0.1383,
"decisionTotal": 6776,
"decisionFailureRate": 0.8615,
"decisionSuccessRate": 0.1385,
"decisionTotal": 6778,
"failureBreakdown": {
"ambiguous_runtime": 3848,
"architecture_compatibility": 212,
@@ -30857,35 +30900,35 @@
"repository_structure": 734,
"runtime_memory": 84,
"tokenizer_compatibility": 659,
"参数/模板问题": 3141,
"参数/模板问题": 3142,
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 15142,
"failureRate": 0.9417,
"failureCount": 15143,
"failureRate": 0.9416,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 922,
"successCount": 937,
"successRate": 0.0583,
"total": 16079,
"unresolvedFailureCount": 8381
"successCount": 939,
"successRate": 0.0584,
"total": 16082,
"unresolvedFailureCount": 8382
},
"warnings": [
"GPU Iluvatar_mrv-100 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。",
"GPU Kunlunxin_p-800 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-100 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 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 Cambricon_mlu-370-x4 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-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 Ascend_910-b4 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 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Sunrise_pt-200-x1|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。",
"组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -30922,6 +30965,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16257,
"summarizedRecords": 16260,
"version": 1
}