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

state: generation 13301 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-23 02:39:48 +00:00
parent d500725e5f
commit cfe96b026f
10 changed files with 1991 additions and 1998 deletions
Download Patch File Download Diff File Expand all files Collapse all files

187
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-23T02:35:36.757931+00:00",
"lastSyncTime": "2026-09-23T02:35:34.755698+00:00",
"generatedAt": "2026-09-23T02:39:33.263628+00:00",
"lastSyncTime": "2026-09-23T02:39:29.759281+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3481,10 +3481,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 106,
"ambiguous_runtime": 107,
"memory_capacity": 1
},
"failureCount": 107,
"failureCount": 108,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -3494,8 +3494,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 107,
"unresolvedFailureCount": 106
"total": 108,
"unresolvedFailureCount": 107
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 44,
@@ -3700,14 +3700,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 12,
"failureBreakdown": {
"ambiguous_runtime": 34,
"ambiguous_runtime": 35,
"framework_architecture_unsupported": 8,
"model_load": 3,
"platform_infrastructure": 2,
"tokenizer_compatibility": 1,
"参数/模板问题": 5
},
"failureCount": 53,
"failureCount": 54,
"failureRate": 1.0,
"framework": "vllm-customized",
"pendingCount": 0,
@@ -3717,8 +3717,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 53,
"unresolvedFailureCount": 39
"total": 54,
"unresolvedFailureCount": 40
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 14,
@@ -5747,22 +5747,22 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 12,
"failureBreakdown": {
"ambiguous_runtime": 34,
"ambiguous_runtime": 35,
"framework_architecture_unsupported": 8,
"model_load": 3,
"platform_infrastructure": 2,
"tokenizer_compatibility": 1,
"参数/模板问题": 5
},
"failureCount": 53,
"failureCount": 54,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 0,
"successRate": 0.0,
"total": 53,
"unresolvedFailureCount": 39
"total": 54,
"unresolvedFailureCount": 40
},
"vllm-mlu": {
"attributableFailureCount": 25,
@@ -5840,7 +5840,7 @@
"decisionSuccessRate": 0.0357,
"decisionTotal": 140,
"failureBreakdown": {
"ambiguous_runtime": 299,
"ambiguous_runtime": 300,
"backend_operator": 9,
"framework_architecture_unsupported": 29,
"memory_capacity": 10,
@@ -5849,15 +5849,15 @@
"tokenizer_compatibility": 82,
"参数/模板问题": 13
},
"failureCount": 466,
"failureCount": 467,
"failureRate": 0.9894,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 19,
"successCount": 5,
"successRate": 0.0106,
"total": 471,
"unresolvedFailureCount": 312
"total": 472,
"unresolvedFailureCount": 313
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 107,
@@ -5888,7 +5888,7 @@
"unresolvedFailureCount": 175
}
},
"generatedAt": "2026-09-23T02:35:36.744395+00:00",
"generatedAt": "2026-09-23T02:39:33.251720+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 102,
@@ -5950,7 +5950,7 @@
"decisionSuccessRate": 0.1179,
"decisionTotal": 212,
"failureBreakdown": {
"ambiguous_runtime": 249,
"ambiguous_runtime": 250,
"backend_operator": 4,
"context_length": 10,
"framework_architecture_unsupported": 120,
@@ -5964,15 +5964,15 @@
"日志缺失": 62,
"验证失败": 27
},
"failureCount": 741,
"failureCount": 742,
"failureRate": 0.9674,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 25,
"successRate": 0.0326,
"total": 766,
"unresolvedFailureCount": 552
"total": 767,
"unresolvedFailureCount": 553
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 723,
@@ -6009,7 +6009,7 @@
"decisionSuccessRate": 0.1892,
"decisionTotal": 74,
"failureBreakdown": {
"ambiguous_runtime": 141,
"ambiguous_runtime": 142,
"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": 266,
"failureRate": 0.95,
"failureCount": 267,
"failureRate": 0.9502,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 14,
"successRate": 0.05,
"total": 280,
"unresolvedFailureCount": 204
"successRate": 0.0498,
"total": 281,
"unresolvedFailureCount": 205
},
"Iluvatar_bi-100": {
"attributableFailureCount": 194,
@@ -9230,9 +9230,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 11
"ambiguous_runtime": 12
},
"failureCount": 11,
"failureCount": 12,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5",
@@ -9244,8 +9244,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 11,
"unresolvedFailureCount": 11
"total": 12,
"unresolvedFailureCount": 12
},
"Biren_166m|vllm_fix_tokenizer|text-generation|qwen3|compressed-tensors": {
"attributableFailureCount": 0,
@@ -11188,9 +11188,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-customized",
"modelType": "phi3",
@@ -11202,8 +11202,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|qwen2|compressed-tensors": {
"attributableFailureCount": 0,
@@ -20888,9 +20888,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 15
"ambiguous_runtime": 13
},
"failureCount": 15,
"failureCount": 13,
"failureRate": 1.0,
"framework": "transformers",
"lastPlatformFailureAt": null,
@@ -20902,8 +20902,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 15,
"unresolvedFailureCount": 15
"total": 13,
"unresolvedFailureCount": 13
},
"Iluvatar_bi-150|transformers|text-generation": {
"attributableFailureCount": 5,
@@ -22230,9 +22230,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 6
"ambiguous_runtime": 7
},
"failureCount": 6,
"failureCount": 7,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-22T16:15:27.384896+00:00",
@@ -22245,8 +22245,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 6,
"unresolvedFailureCount": 6
"total": 7,
"unresolvedFailureCount": 7
},
"Biren_166m|vllm_fix_tokenizer|text-generation|qwen3|compressed-tensors": {
"attributableFailureCount": 0,
@@ -22755,12 +22755,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-customized",
"lastTerminalAt": "2026-09-22T13:13:03.464336+00:00",
"lastTerminalAt": "2026-09-23T02:39:29.759268+00:00",
"modelType": "phi3",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -22770,8 +22770,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|qwen2|compressed-tensors": {
"attributableFailureCount": 0,
@@ -23080,9 +23080,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
"ambiguous_runtime": 2
},
"failureCount": 3,
"failureCount": 2,
"failureRate": 1.0,
"framework": "transformers",
"lastTerminalAt": "2026-09-21T05:42:03.443575+00:00",
@@ -23095,33 +23095,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
},
"Iluvatar_bi-100|transformers|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": "transformers",
"lastTerminalAt": "2026-09-21T05:14:26.178418+00:00",
"modelType": "qwen3_vl",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Iluvatar_bi-100|transformers|text-generation|sophia_hybrid|none": {
"attributableFailureCount": 0,
@@ -29046,9 +29021,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 6
"ambiguous_runtime": 7
},
"failureCount": 6,
"failureCount": 7,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 34,
@@ -29061,8 +29036,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 6,
"unresolvedFailureCount": 6
"total": 7,
"unresolvedFailureCount": 7
},
"Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5|none|35": {
"attributableFailureCount": 0,
@@ -31888,6 +31863,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|phi3|compressed-tensors|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-customized",
"loadSizeLog2Bucket": 31,
"modelType": "phi3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"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|phi3|compressed-tensors|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -45826,15 +45825,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16796,
"totalRecords": 17014,
"terminalRecords": 16798,
"totalRecords": 17016,
"totals": {
"attributableFailureCount": 6013,
"decisionFailureRate": 0.8622,
"decisionSuccessRate": 0.1378,
"decisionTotal": 6974,
"failureBreakdown": {
"ambiguous_runtime": 4283,
"ambiguous_runtime": 4285,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 115,
@@ -45850,20 +45849,19 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 15835,
"failureCount": 15837,
"failureRate": 0.9428,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 931,
"successCount": 961,
"successRate": 0.0572,
"total": 16796,
"unresolvedFailureCount": 8891
"total": 16798,
"unresolvedFailureCount": 8893
},
"warnings": [
"GPU Iluvatar_mrv-100 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 Biren_166m 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 Cambricon_mlu-370-x8 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。",
@@ -45872,8 +45870,9 @@
"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 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 Ascend_910-b4 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。",
"组合 Sunrise_pt-200-x1|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -45897,6 +45896,7 @@
"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。",
@@ -45910,11 +45910,10 @@
"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 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 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。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17014,
"summarizedRecords": 17016,
"version": 1
}