CoolBoy/submmit
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

state: generation 13304 (intent)

Browse Source
This commit is contained in:
CoolBoy
2026-09-23 02:44:28 +00:00
parent d2145b06c6
commit e59293110d
8 changed files with 145 additions and 81 deletions
Download Patch File Download Diff File Expand all files Collapse all files

142
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-23T02:39:33.263628+00:00",
"lastSyncTime": "2026-09-23T02:39:29.759281+00:00",
"generatedAt": "2026-09-23T02:43:28.816899+00:00",
"lastSyncTime": "2026-09-23T02:43:25.562726+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3700,14 +3700,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 12,
"failureBreakdown": {
"ambiguous_runtime": 35,
"ambiguous_runtime": 36,
"framework_architecture_unsupported": 8,
"model_load": 3,
"platform_infrastructure": 2,
"tokenizer_compatibility": 1,
"参数/模板问题": 5
},
"failureCount": 54,
"failureCount": 55,
"failureRate": 1.0,
"framework": "vllm-customized",
"pendingCount": 0,
@@ -3717,8 +3717,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 54,
"unresolvedFailureCount": 40
"total": 55,
"unresolvedFailureCount": 41
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 14,
@@ -5747,22 +5747,22 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 12,
"failureBreakdown": {
"ambiguous_runtime": 35,
"ambiguous_runtime": 36,
"framework_architecture_unsupported": 8,
"model_load": 3,
"platform_infrastructure": 2,
"tokenizer_compatibility": 1,
"参数/模板问题": 5
},
"failureCount": 54,
"failureCount": 55,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 0,
"successRate": 0.0,
"total": 54,
"unresolvedFailureCount": 40
"total": 55,
"unresolvedFailureCount": 41
},
"vllm-mlu": {
"attributableFailureCount": 25,
@@ -5888,7 +5888,7 @@
"unresolvedFailureCount": 175
}
},
"generatedAt": "2026-09-23T02:39:33.251720+00:00",
"generatedAt": "2026-09-23T02:43:28.804947+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 102,
@@ -6009,7 +6009,7 @@
"decisionSuccessRate": 0.1892,
"decisionTotal": 74,
"failureBreakdown": {
"ambiguous_runtime": 142,
"ambiguous_runtime": 143,
"framework_architecture_unsupported": 48,
"memory_capacity": 4,
"model_load": 5,
@@ -6018,15 +6018,15 @@
"参数/模板问题": 41,
"验证失败": 22
},
"failureCount": 267,
"failureRate": 0.9502,
"failureCount": 268,
"failureRate": 0.9504,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 14,
"successRate": 0.0498,
"total": 281,
"unresolvedFailureCount": 205
"successRate": 0.0496,
"total": 282,
"unresolvedFailureCount": 206
},
"Iluvatar_bi-100": {
"attributableFailureCount": 194,
@@ -11321,6 +11321,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|qwen3_vl|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-customized",
"modelType": "qwen3_vl",
"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": 1
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|sophia_hybrid|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -20888,9 +20911,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 13
"ambiguous_runtime": 12
},
"failureCount": 13,
"failureCount": 12,
"failureRate": 1.0,
"framework": "transformers",
"lastPlatformFailureAt": null,
@@ -20902,8 +20925,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 13,
"unresolvedFailureCount": 13
"total": 12,
"unresolvedFailureCount": 12
},
"Iluvatar_bi-150|transformers|text-generation": {
"attributableFailureCount": 5,
@@ -22798,6 +22821,31 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|qwen3_vl|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-customized",
"lastTerminalAt": "2026-09-23T02:43:25.562726+00:00",
"modelType": "qwen3_vl",
"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": 1
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|sophia_hybrid|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -22980,9 +23028,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 5
"ambiguous_runtime": 4
},
"failureCount": 5,
"failureCount": 4,
"failureRate": 1.0,
"framework": "transformers",
"lastTerminalAt": "2026-09-21T05:42:03.443548+00:00",
@@ -22995,8 +23043,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 5
"total": 4,
"unresolvedFailureCount": 4
},
"Iluvatar_bi-100|transformers|text-generation|lfm2|none": {
"attributableFailureCount": 0,
@@ -32080,6 +32128,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|qwen3_vl|none|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-customized",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_vl",
"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": 1
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|sophia_hybrid|none|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -45825,15 +45897,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16798,
"totalRecords": 17016,
"terminalRecords": 16799,
"totalRecords": 17017,
"totals": {
"attributableFailureCount": 6013,
"decisionFailureRate": 0.8622,
"decisionSuccessRate": 0.1378,
"decisionTotal": 6974,
"failureBreakdown": {
"ambiguous_runtime": 4285,
"ambiguous_runtime": 4286,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 115,
@@ -45849,15 +45921,15 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 15837,
"failureCount": 15838,
"failureRate": 0.9428,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 931,
"successCount": 961,
"successRate": 0.0572,
"total": 16798,
"unresolvedFailureCount": 8893
"total": 16799,
"unresolvedFailureCount": 8894
},
"warnings": [
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -45870,8 +45942,8 @@
"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 Vastai_va16 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 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 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。",
"组合 Iluvatar_bi-150|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。",
@@ -45896,7 +45968,6 @@
"组合 Ascend_910-b4|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"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 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。",
"组合 Ascend_910-b3|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 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 Sunrise_pt-200-x1|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -45910,10 +45981,11 @@
"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|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 MetaX_c-500|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 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 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 Ascend_910-b3|vllm|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": 17016,
"summarizedRecords": 17017,
"version": 1
}