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

state: generation 10635 (intent)

Browse Source
This commit is contained in:
CoolBoy
2026-09-20 14:48:04 +00:00
parent 646d2131fa
commit 3b06c798fe
8 changed files with 191 additions and 133 deletions
Download Patch File Download Diff File Expand all files Collapse all files

158
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-20T14:34:58.328009+00:00",
"lastSyncTime": "2026-09-20T14:34:57.856745+00:00",
"generatedAt": "2026-09-20T14:47:45.558449+00:00",
"lastSyncTime": "2026-09-20T14:47:45.260018+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3145,10 +3145,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 24,
"ambiguous_runtime": 25,
"memory_capacity": 7
},
"failureCount": 31,
"failureCount": 32,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -3158,8 +3158,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 31,
"unresolvedFailureCount": 24
"total": 32,
"unresolvedFailureCount": 25
},
"Iluvatar_bi-150|vllm|reinforcement_learning": {
"attributableFailureCount": 0,
@@ -3484,10 +3484,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 82,
"ambiguous_runtime": 83,
"参数/模板问题": 2
},
"failureCount": 84,
"failureCount": 85,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -3497,8 +3497,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 84,
"unresolvedFailureCount": 84
"total": 85,
"unresolvedFailureCount": 85
},
"Kunlunxin_r-200-8f|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -4575,7 +4575,7 @@
"decisionSuccessRate": 0.0167,
"decisionTotal": 120,
"failureBreakdown": {
"ambiguous_runtime": 117,
"ambiguous_runtime": 119,
"backend_operator": 8,
"framework_architecture_unsupported": 20,
"memory_capacity": 7,
@@ -4584,15 +4584,15 @@
"tokenizer_compatibility": 82,
"参数/模板问题": 8
},
"failureCount": 259,
"failureRate": 0.9923,
"failureCount": 261,
"failureRate": 0.9924,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 16,
"successCount": 2,
"successRate": 0.0077,
"total": 261,
"unresolvedFailureCount": 125
"successRate": 0.0076,
"total": 263,
"unresolvedFailureCount": 127
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 26,
@@ -4614,7 +4614,7 @@
"unresolvedFailureCount": 24
}
},
"generatedAt": "2026-09-20T14:34:58.319961+00:00",
"generatedAt": "2026-09-20T14:47:45.550467+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 75,
@@ -4781,7 +4781,7 @@
"decisionSuccessRate": 0.1701,
"decisionTotal": 876,
"failureBreakdown": {
"ambiguous_runtime": 604,
"ambiguous_runtime": 605,
"architecture_compatibility": 15,
"backend_operator": 11,
"context_length": 29,
@@ -4796,15 +4796,15 @@
"日志缺失": 155,
"验证失败": 30
},
"failureCount": 1856,
"failureCount": 1857,
"failureRate": 0.9257,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 21,
"successCount": 149,
"successRate": 0.0743,
"total": 2005,
"unresolvedFailureCount": 1108
"total": 2006,
"unresolvedFailureCount": 1109
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 964,
@@ -4843,21 +4843,21 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 156,
"ambiguous_runtime": 157,
"memory_capacity": 1,
"参数/模板问题": 2,
"日志缺失": 1,
"验证失败": 23
},
"failureCount": 183,
"failureCount": 184,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 183,
"unresolvedFailureCount": 182
"total": 184,
"unresolvedFailureCount": 183
},
"Kunlunxin_r-200-8f": {
"attributableFailureCount": 0,
@@ -7958,6 +7958,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|bailing_hybrid|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": "bailing_hybrid",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|gemma4_unified|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -9208,10 +9231,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 8,
"ambiguous_runtime": 9,
"参数/模板问题": 1
},
"failureCount": 9,
"failureCount": 10,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5",
@@ -9223,8 +9246,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 9,
"unresolvedFailureCount": 9
"total": 10,
"unresolvedFailureCount": 10
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3|none": {
"attributableFailureCount": 0,
@@ -11370,7 +11393,7 @@
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-20T13:30:42.155978+00:00",
"lastTerminalAt": "2026-09-20T14:47:45.260018+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -12476,6 +12499,31 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|bailing_hybrid|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": "2026-09-20T14:47:45.260018+00:00",
"modelType": "bailing_hybrid",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|gemma4_unified|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -17368,6 +17416,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|bailing_hybrid|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": "bailing_hybrid",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|gemma4_unified|none|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -19244,9 +19316,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
"ambiguous_runtime": 4
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 33,
@@ -19259,8 +19331,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 4,
"unresolvedFailureCount": 4
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|none|34": {
"attributableFailureCount": 0,
@@ -22195,15 +22267,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 15870,
"totalRecords": 15975,
"terminalRecords": 15872,
"totalRecords": 15977,
"totals": {
"attributableFailureCount": 5755,
"decisionFailureRate": 0.8614,
"decisionSuccessRate": 0.1386,
"decisionTotal": 6681,
"failureBreakdown": {
"ambiguous_runtime": 3765,
"ambiguous_runtime": 3767,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 102,
@@ -22219,15 +22291,15 @@
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 14944,
"failureCount": 14946,
"failureRate": 0.9417,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 922,
"successCount": 926,
"successRate": 0.0583,
"total": 15870,
"unresolvedFailureCount": 8267
"total": 15872,
"unresolvedFailureCount": 8269
},
"warnings": [
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -22272,12 +22344,12 @@
"组合 Cambricon_mlu-370-x4|unknown|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 Ascend_910-b4|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|transformers|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 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 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-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 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。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 15975,
"summarizedRecords": 15977,
"version": 1
}