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

state: generation 10616 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-20 14:18:10 +00:00
parent 4826fb7212
commit d9eca51531
9 changed files with 1960 additions and 1940 deletions
Download Patch File Download Diff File Expand all files Collapse all files

171
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-20T14:14:39.977491+00:00",
"lastSyncTime": "2026-09-20T14:14:39.678936+00:00",
"generatedAt": "2026-09-20T14:18:03.550019+00:00",
"lastSyncTime": "2026-09-20T14:18:03.259028+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1497,7 +1497,7 @@
"sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|model_type:qwen3_5": {
"architectureSignature": "model_type:qwen3_5",
"architectures": [],
"evidenceCount": 2,
"evidenceCount": 1,
"expiresAt": "2026-10-16T01:37:21+00:00",
"framework": "vllm_fix_tokenizer",
"latestFailureAt": "2026-09-16T01:37:21+00:00",
@@ -1505,12 +1505,10 @@
"matchType": "model_type",
"modelType": "qwen3_5",
"sourceModelIds": [
"Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed",
"Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16"
"Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed"
],
"sourceTaskIds": [
"4337531",
"4336358"
"4337531"
],
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation"
@@ -2236,15 +2234,15 @@
"unresolvedFailureCount": 17
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 11,
"attributableFailureCount": 12,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 11,
"decisionTotal": 12,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 11
"framework_architecture_unsupported": 12
},
"failureCount": 28,
"failureCount": 29,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
@@ -2254,7 +2252,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 28,
"total": 29,
"unresolvedFailureCount": 17
},
"Ascend_910-b4|vllm|text-generation": {
@@ -3649,7 +3647,7 @@
"decisionSuccessRate": 0.0359,
"decisionTotal": 641,
"failureBreakdown": {
"ambiguous_runtime": 124,
"ambiguous_runtime": 125,
"architecture_compatibility": 20,
"backend_operator": 43,
"context_length": 46,
@@ -3661,7 +3659,7 @@
"tokenizer_compatibility": 78,
"参数/模板问题": 9
},
"failureCount": 754,
"failureCount": 755,
"failureRate": 0.9704,
"framework": "vllm",
"pendingCount": 0,
@@ -3671,8 +3669,8 @@
"successRate": 0.0296,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 777,
"unresolvedFailureCount": 133
"total": 778,
"unresolvedFailureCount": 134
},
"MetaX_c-500|vllm|unknown": {
"attributableFailureCount": 1,
@@ -4463,7 +4461,7 @@
"decisionSuccessRate": 0.0217,
"decisionTotal": 3551,
"failureBreakdown": {
"ambiguous_runtime": 1429,
"ambiguous_runtime": 1430,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
@@ -4477,15 +4475,15 @@
"tokenizer_compatibility": 408,
"参数/模板问题": 40
},
"failureCount": 5807,
"failureCount": 5808,
"failureRate": 0.9869,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 864,
"successCount": 77,
"successRate": 0.0131,
"total": 5884,
"unresolvedFailureCount": 1469
"total": 5885,
"unresolvedFailureCount": 1470
},
"vllm-customized": {
"attributableFailureCount": 1,
@@ -4599,26 +4597,26 @@
"unresolvedFailureCount": 123
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 25,
"decisionFailureRate": 0.9259,
"decisionSuccessRate": 0.0741,
"decisionTotal": 27,
"attributableFailureCount": 26,
"decisionFailureRate": 0.9286,
"decisionSuccessRate": 0.0714,
"decisionTotal": 28,
"failureBreakdown": {
"ambiguous_runtime": 24,
"framework_architecture_unsupported": 25
"framework_architecture_unsupported": 26
},
"failureCount": 49,
"failureRate": 0.9608,
"failureCount": 50,
"failureRate": 0.9615,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0392,
"total": 51,
"successRate": 0.0385,
"total": 52,
"unresolvedFailureCount": 24
}
},
"generatedAt": "2026-09-20T14:14:39.968836+00:00",
"generatedAt": "2026-09-20T14:18:03.541951+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 75,
@@ -4646,14 +4644,14 @@
"unresolvedFailureCount": 108
},
"Ascend_910-b4": {
"attributableFailureCount": 304,
"decisionFailureRate": 0.8306,
"decisionSuccessRate": 0.1694,
"decisionTotal": 366,
"attributableFailureCount": 305,
"decisionFailureRate": 0.8311,
"decisionSuccessRate": 0.1689,
"decisionTotal": 367,
"failureBreakdown": {
"ambiguous_runtime": 145,
"context_length": 1,
"framework_architecture_unsupported": 164,
"framework_architecture_unsupported": 165,
"memory_capacity": 18,
"model_load": 85,
"platform_infrastructure": 1,
@@ -4663,14 +4661,14 @@
"日志缺失": 14,
"验证失败": 175
},
"failureCount": 893,
"failureCount": 894,
"failureRate": 0.9351,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 62,
"successRate": 0.0649,
"total": 955,
"total": 956,
"unresolvedFailureCount": 588
},
"Biren_166m": {
@@ -4888,7 +4886,7 @@
"decisionSuccessRate": 0.1807,
"decisionTotal": 797,
"failureBreakdown": {
"ambiguous_runtime": 296,
"ambiguous_runtime": 297,
"architecture_compatibility": 21,
"backend_operator": 43,
"context_length": 59,
@@ -4902,15 +4900,15 @@
"日志缺失": 15,
"验证失败": 48
},
"failureCount": 1415,
"failureRate": 0.9076,
"failureCount": 1416,
"failureRate": 0.9077,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 5,
"successCount": 144,
"successRate": 0.0924,
"total": 1559,
"unresolvedFailureCount": 757
"successRate": 0.0923,
"total": 1560,
"unresolvedFailureCount": 758
},
"Mthreads_s4000": {
"attributableFailureCount": 69,
@@ -5620,14 +5618,14 @@
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|none": {
"attributableFailureCount": 2,
"attributableFailureCount": 3,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {
"framework_architecture_unsupported": 2
"framework_architecture_unsupported": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "qwen3_5",
@@ -5639,7 +5637,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3|none": {
@@ -11454,14 +11452,15 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 1,
"backend_operator": 1,
"tokenizer_compatibility": 1
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-20T13:34:22.859810+00:00",
"lastTerminalAt": "2026-09-20T14:18:03.259001+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -11469,8 +11468,8 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 0
"total": 3,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -11552,18 +11551,18 @@
"unresolvedFailureCount": 1
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 9,
"consecutiveFailures": 9,
"attributableFailureCount": 8,
"consecutiveFailures": 8,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 9,
"decisionTotal": 8,
"failureBreakdown": {
"framework_architecture_unsupported": 3,
"framework_architecture_unsupported": 2,
"platform_infrastructure": 3,
"tokenizer_compatibility": 6
},
"failureCount": 12,
"failureCount": 11,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": "2026-09-16T02:03:21+00:00",
@@ -11575,7 +11574,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 12,
"total": 11,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -13824,6 +13823,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|none|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -21942,20 +21965,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 15862,
"totalRecords": 15967,
"terminalRecords": 15864,
"totalRecords": 15969,
"totals": {
"attributableFailureCount": 5754,
"decisionFailureRate": 0.8616,
"decisionSuccessRate": 0.1384,
"decisionTotal": 6678,
"attributableFailureCount": 5755,
"decisionFailureRate": 0.8617,
"decisionSuccessRate": 0.1383,
"decisionTotal": 6679,
"failureBreakdown": {
"ambiguous_runtime": 3760,
"ambiguous_runtime": 3761,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 102,
"context_length": 318,
"framework_architecture_unsupported": 1984,
"framework_architecture_unsupported": 1985,
"memory_capacity": 1195,
"model_load": 478,
"platform_infrastructure": 922,
@@ -21966,15 +21989,15 @@
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 14938,
"failureRate": 0.9417,
"failureCount": 14940,
"failureRate": 0.9418,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 922,
"successCount": 924,
"successRate": 0.0583,
"total": 15862,
"unresolvedFailureCount": 8262
"successRate": 0.0582,
"total": 15864,
"unresolvedFailureCount": 8263
},
"warnings": [
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -22019,12 +22042,12 @@
"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 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 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": 15967,
"summarizedRecords": 15969,
"version": 1
}