state: generation 11320 (cycle)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-21T07:36:10.361847+00:00",
|
||||
"lastSyncTime": "2026-09-21T07:35:50.256608+00:00",
|
||||
"generatedAt": "2026-09-21T07:56:18.500367+00:00",
|
||||
"lastSyncTime": "2026-09-21T07:56:18.163712+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -3045,6 +3045,27 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Biren_166m|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3
|
||||
},
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Biren_166m|vllm|text-generation": {
|
||||
"attributableFailureCount": 41,
|
||||
"decisionFailureRate": 0.7321,
|
||||
@@ -4592,14 +4613,14 @@
|
||||
"unresolvedFailureCount": 158
|
||||
},
|
||||
"Mthreads_s4000|vllm|text-generation": {
|
||||
"attributableFailureCount": 67,
|
||||
"decisionFailureRate": 0.7614,
|
||||
"decisionSuccessRate": 0.2386,
|
||||
"decisionTotal": 88,
|
||||
"attributableFailureCount": 68,
|
||||
"decisionFailureRate": 0.764,
|
||||
"decisionSuccessRate": 0.236,
|
||||
"decisionTotal": 89,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 61,
|
||||
"backend_operator": 8,
|
||||
"framework_architecture_unsupported": 49,
|
||||
"framework_architecture_unsupported": 50,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 2,
|
||||
"repository_structure": 1,
|
||||
@@ -4607,17 +4628,17 @@
|
||||
"tokenizer_compatibility": 1,
|
||||
"参数/模板问题": 12
|
||||
},
|
||||
"failureCount": 140,
|
||||
"failureRate": 0.8696,
|
||||
"failureCount": 141,
|
||||
"failureRate": 0.8704,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 21,
|
||||
"successRate": 0.1304,
|
||||
"successRate": 0.1296,
|
||||
"targetGpu": "Mthreads_s4000",
|
||||
"taskType": "text-generation",
|
||||
"total": 161,
|
||||
"total": 162,
|
||||
"unresolvedFailureCount": 73
|
||||
},
|
||||
"Mthreads_s4000|vllm|visual-multi-modal": {
|
||||
@@ -5240,17 +5261,17 @@
|
||||
"unresolvedFailureCount": 6442
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 3517,
|
||||
"attributableFailureCount": 3518,
|
||||
"decisionFailureRate": 0.9764,
|
||||
"decisionSuccessRate": 0.0236,
|
||||
"decisionTotal": 3602,
|
||||
"decisionTotal": 3603,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1471,
|
||||
"architecture_compatibility": 112,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 84,
|
||||
"context_length": 161,
|
||||
"framework_architecture_unsupported": 1289,
|
||||
"framework_architecture_unsupported": 1290,
|
||||
"memory_capacity": 720,
|
||||
"model_load": 206,
|
||||
"platform_infrastructure": 865,
|
||||
@@ -5259,14 +5280,14 @@
|
||||
"tokenizer_compatibility": 410,
|
||||
"参数/模板问题": 41
|
||||
},
|
||||
"failureCount": 5894,
|
||||
"failureCount": 5895,
|
||||
"failureRate": 0.9858,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 865,
|
||||
"successCount": 85,
|
||||
"successRate": 0.0142,
|
||||
"total": 5979,
|
||||
"total": 5980,
|
||||
"unresolvedFailureCount": 1512
|
||||
},
|
||||
"vllm-customized": {
|
||||
@@ -5365,7 +5386,7 @@
|
||||
"decisionSuccessRate": 0.0397,
|
||||
"decisionTotal": 126,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 136,
|
||||
"ambiguous_runtime": 139,
|
||||
"backend_operator": 8,
|
||||
"framework_architecture_unsupported": 22,
|
||||
"memory_capacity": 7,
|
||||
@@ -5374,15 +5395,15 @@
|
||||
"tokenizer_compatibility": 82,
|
||||
"参数/模板问题": 9
|
||||
},
|
||||
"failureCount": 282,
|
||||
"failureRate": 0.9826,
|
||||
"failureCount": 285,
|
||||
"failureRate": 0.9828,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 16,
|
||||
"successCount": 5,
|
||||
"successRate": 0.0174,
|
||||
"total": 287,
|
||||
"unresolvedFailureCount": 145
|
||||
"successRate": 0.0172,
|
||||
"total": 290,
|
||||
"unresolvedFailureCount": 148
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
"attributableFailureCount": 59,
|
||||
@@ -5409,7 +5430,7 @@
|
||||
"unresolvedFailureCount": 67
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-21T07:36:10.351855+00:00",
|
||||
"generatedAt": "2026-09-21T07:56:18.490311+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 91,
|
||||
@@ -5471,7 +5492,7 @@
|
||||
"decisionSuccessRate": 0.1214,
|
||||
"decisionTotal": 206,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 139,
|
||||
"ambiguous_runtime": 142,
|
||||
"backend_operator": 4,
|
||||
"context_length": 10,
|
||||
"framework_architecture_unsupported": 116,
|
||||
@@ -5485,15 +5506,15 @@
|
||||
"日志缺失": 62,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 625,
|
||||
"failureRate": 0.9615,
|
||||
"failureCount": 628,
|
||||
"failureRate": 0.9617,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 25,
|
||||
"successRate": 0.0385,
|
||||
"total": 650,
|
||||
"unresolvedFailureCount": 442
|
||||
"successRate": 0.0383,
|
||||
"total": 653,
|
||||
"unresolvedFailureCount": 445
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"attributableFailureCount": 714,
|
||||
@@ -5707,14 +5728,14 @@
|
||||
"unresolvedFailureCount": 762
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"attributableFailureCount": 71,
|
||||
"decisionFailureRate": 0.6339,
|
||||
"decisionSuccessRate": 0.3661,
|
||||
"decisionTotal": 112,
|
||||
"attributableFailureCount": 72,
|
||||
"decisionFailureRate": 0.6372,
|
||||
"decisionSuccessRate": 0.3628,
|
||||
"decisionTotal": 113,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 107,
|
||||
"backend_operator": 8,
|
||||
"framework_architecture_unsupported": 50,
|
||||
"framework_architecture_unsupported": 51,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 5,
|
||||
"repository_structure": 1,
|
||||
@@ -5724,14 +5745,14 @@
|
||||
"日志缺失": 96,
|
||||
"验证失败": 26
|
||||
},
|
||||
"failureCount": 356,
|
||||
"failureRate": 0.8967,
|
||||
"failureCount": 357,
|
||||
"failureRate": 0.897,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 41,
|
||||
"successRate": 0.1033,
|
||||
"total": 397,
|
||||
"successRate": 0.103,
|
||||
"total": 398,
|
||||
"unresolvedFailureCount": 285
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
@@ -7175,6 +7196,75 @@
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Biren_166m|vllm_fix_tokenizer|text-generation|gemma4_unified|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"modelType": "gemma4_unified",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Biren_166m|vllm_fix_tokenizer|text-generation|llama|awq": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"modelType": "llama",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "awq",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Biren_166m|vllm_fix_tokenizer|text-generation|qwen2|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"modelType": "qwen2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|cohere2|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -15036,6 +15126,31 @@
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Biren_166m|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3
|
||||
},
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-21T07:56:18.163682+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Biren_166m|vllm|text-generation": {
|
||||
"attributableFailureCount": 7,
|
||||
"consecutiveFailures": 7,
|
||||
@@ -15355,31 +15470,6 @@
|
||||
"total": 7,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Iluvatar_mrv-100|vllm|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-21T02:15:17.867341+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Kunlunxin_p-800|unknown|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
@@ -15510,30 +15600,30 @@
|
||||
"unresolvedFailureCount": 5
|
||||
},
|
||||
"Mthreads_s4000|vllm|text-generation": {
|
||||
"attributableFailureCount": 2,
|
||||
"consecutiveFailures": 2,
|
||||
"attributableFailureCount": 3,
|
||||
"consecutiveFailures": 3,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.6667,
|
||||
"decisionSuccessRate": 0.3333,
|
||||
"decisionTotal": 3,
|
||||
"decisionFailureRate": 0.75,
|
||||
"decisionSuccessRate": 0.25,
|
||||
"decisionTotal": 4,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2,
|
||||
"framework_architecture_unsupported": 1,
|
||||
"framework_architecture_unsupported": 2,
|
||||
"runtime_memory": 1
|
||||
},
|
||||
"failureCount": 4,
|
||||
"failureRate": 0.8,
|
||||
"failureCount": 5,
|
||||
"failureRate": 0.8333,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-20T22:20:31.465723+00:00",
|
||||
"lastTerminalAt": "2026-09-21T07:56:18.163712+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.2,
|
||||
"successRate": 0.1667,
|
||||
"targetGpu": "Mthreads_s4000",
|
||||
"taskType": "text-generation",
|
||||
"total": 5,
|
||||
"total": 6,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Sunrise_pt-200-x1|unknown|text-generation": {
|
||||
@@ -15635,20 +15725,18 @@
|
||||
"unresolvedFailureCount": 9
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
|
||||
"attributableFailureCount": 6,
|
||||
"consecutiveFailures": 6,
|
||||
"attributableFailureCount": 4,
|
||||
"consecutiveFailures": 4,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 6,
|
||||
"decisionTotal": 4,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2,
|
||||
"framework_architecture_unsupported": 1,
|
||||
"model_load": 3,
|
||||
"repository_structure": 1,
|
||||
"runtime_memory": 1
|
||||
"repository_structure": 1
|
||||
},
|
||||
"failureCount": 8,
|
||||
"failureCount": 6,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -15660,7 +15748,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 8,
|
||||
"total": 6,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"hygon_k100-ai|vllm|text-generation": {
|
||||
@@ -15994,6 +16082,81 @@
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Biren_166m|vllm_fix_tokenizer|text-generation|gemma4_unified|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastTerminalAt": "2026-09-21T07:56:18.163660+00:00",
|
||||
"modelType": "gemma4_unified",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Biren_166m|vllm_fix_tokenizer|text-generation|llama|awq": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastTerminalAt": "2026-09-21T07:56:18.163682+00:00",
|
||||
"modelType": "llama",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "awq",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Biren_166m|vllm_fix_tokenizer|text-generation|qwen2|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastTerminalAt": "2026-09-21T07:56:18.163617+00:00",
|
||||
"modelType": "qwen2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|gemma3|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
@@ -16596,31 +16759,6 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm|text-generation|cohere2|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastTerminalAt": "2026-09-20T17:09:45.266177+00:00",
|
||||
"modelType": "cohere2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm|text-generation|hrm_text|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
@@ -18750,31 +18888,6 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Iluvatar_mrv-100|vllm|text-generation|llama|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastTerminalAt": "2026-09-21T02:15:17.867341+00:00",
|
||||
"modelType": "llama",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|minicpm|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
@@ -19123,56 +19236,6 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen2|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"runtime_memory": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"lastTerminalAt": "2026-09-20T19:56:29.962443+00:00",
|
||||
"modelType": "qwen2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_moe|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"lastTerminalAt": "2026-09-20T18:53:01.473075+00:00",
|
||||
"modelType": "qwen3_5_moe",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
@@ -21213,6 +21276,78 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Biren_166m|vllm_fix_tokenizer|text-generation|gemma4_unified|none|33": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
"modelType": "gemma4_unified",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Biren_166m|vllm_fix_tokenizer|text-generation|llama|awq|32": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
"modelType": "llama",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "awq",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Biren_166m|vllm_fix_tokenizer|text-generation|qwen2|none|34": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"loadSizeLog2Bucket": 34,
|
||||
"modelType": "qwen2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|cohere2|none|32": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -32312,20 +32447,20 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 16168,
|
||||
"totalRecords": 16350,
|
||||
"terminalRecords": 16172,
|
||||
"totalRecords": 16354,
|
||||
"totals": {
|
||||
"attributableFailureCount": 5855,
|
||||
"attributableFailureCount": 5856,
|
||||
"decisionFailureRate": 0.8614,
|
||||
"decisionSuccessRate": 0.1386,
|
||||
"decisionTotal": 6797,
|
||||
"decisionTotal": 6798,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3884,
|
||||
"ambiguous_runtime": 3887,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 102,
|
||||
"context_length": 319,
|
||||
"framework_architecture_unsupported": 2052,
|
||||
"framework_architecture_unsupported": 2053,
|
||||
"memory_capacity": 1197,
|
||||
"model_load": 494,
|
||||
"platform_infrastructure": 923,
|
||||
@@ -32336,31 +32471,31 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 674
|
||||
},
|
||||
"failureCount": 15226,
|
||||
"failureRate": 0.9417,
|
||||
"failureCount": 15230,
|
||||
"failureRate": 0.9418,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 923,
|
||||
"successCount": 942,
|
||||
"successRate": 0.0583,
|
||||
"total": 16168,
|
||||
"unresolvedFailureCount": 8448
|
||||
"successRate": 0.0582,
|
||||
"total": 16172,
|
||||
"unresolvedFailureCount": 8451
|
||||
},
|
||||
"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 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。",
|
||||
"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。",
|
||||
@@ -32399,6 +32534,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 16350,
|
||||
"summarizedRecords": 16354,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user