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

state: generation 11205 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-21 05:18:00 +00:00
parent 83a28056c4
commit 584598630b
9 changed files with 1921 additions and 1809 deletions
Download Patch File Download Diff File Expand all files Collapse all files

392
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T05:14:26.473344+00:00",
"lastSyncTime": "2026-09-21T05:14:26.178418+00:00",
"generatedAt": "2026-09-21T05:17:51.754913+00:00",
"lastSyncTime": "2026-09-21T05:17:51.457662+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3310,9 +3310,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 37
"ambiguous_runtime": 41
},
"failureCount": 37,
"failureCount": 41,
"failureRate": 1.0,
"framework": "transformers",
"pendingCount": 0,
@@ -3322,8 +3322,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 37,
"unresolvedFailureCount": 37
"total": 41,
"unresolvedFailureCount": 41
},
"Iluvatar_bi-100|unknown|feature_emb": {
"attributableFailureCount": 0,
@@ -5184,21 +5184,21 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 46,
"ambiguous_runtime": 50,
"framework_architecture_unsupported": 7,
"memory_capacity": 5,
"model_load": 2,
"tokenizer_compatibility": 8
},
"failureCount": 68,
"failureCount": 72,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 68,
"unresolvedFailureCount": 46
"total": 72,
"unresolvedFailureCount": 50
},
"unknown": {
"attributableFailureCount": 1858,
@@ -5399,7 +5399,7 @@
"unresolvedFailureCount": 67
}
},
"generatedAt": "2026-09-21T05:14:26.462904+00:00",
"generatedAt": "2026-09-21T05:17:51.744207+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 91,
@@ -5544,22 +5544,22 @@
"decisionSuccessRate": 0.2392,
"decisionTotal": 255,
"failureBreakdown": {
"ambiguous_runtime": 157,
"ambiguous_runtime": 161,
"memory_capacity": 194,
"platform_infrastructure": 635,
"参数/模板问题": 242,
"日志缺失": 134,
"验证失败": 20
},
"failureCount": 1382,
"failureRate": 0.9577,
"failureCount": 1386,
"failureRate": 0.9578,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 635,
"successCount": 61,
"successRate": 0.0423,
"total": 1443,
"unresolvedFailureCount": 553
"successRate": 0.0422,
"total": 1447,
"unresolvedFailureCount": 557
},
"Iluvatar_bi-150": {
"attributableFailureCount": 739,
@@ -9304,6 +9304,75 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-100|transformers|text-generation|gemma4|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "transformers",
"modelType": "gemma4",
"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
},
"Iluvatar_bi-100|transformers|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "transformers",
"modelType": "qwen3_5_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
},
"Iluvatar_bi-100|transformers|text-generation|qwen3_5|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "transformers",
"modelType": "qwen3_5",
"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
},
"Iluvatar_bi-100|transformers|text-generation|qwen3_vl|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -14868,13 +14937,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 6
},
"failureCount": 2,
"failureCount": 6,
"failureRate": 1.0,
"framework": "transformers",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T05:14:26.178403+00:00",
"lastTerminalAt": "2026-09-21T05:17:51.457662+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -14882,8 +14951,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 6,
"unresolvedFailureCount": 6
},
"Iluvatar_bi-150|transformers|text-generation": {
"attributableFailureCount": 14,
@@ -15080,9 +15149,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 4
"ambiguous_runtime": 2
},
"failureCount": 4,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
@@ -15094,8 +15163,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 4
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 8,
@@ -16962,6 +17031,81 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-100|transformers|text-generation|gemma4|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": "2026-09-21T05:17:51.457647+00:00",
"modelType": "gemma4",
"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
},
"Iluvatar_bi-100|transformers|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "transformers",
"lastTerminalAt": "2026-09-21T05:17:51.457662+00:00",
"modelType": "qwen3_5_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
},
"Iluvatar_bi-100|transformers|text-generation|qwen3_5|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": "2026-09-21T05:17:51.457611+00:00",
"modelType": "qwen3_5",
"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
},
"Iluvatar_bi-100|transformers|text-generation|qwen3_vl|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -18566,31 +18710,6 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|hyperclovax_vision_v2|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": "2026-09-20T18:18:38.666126+00:00",
"modelType": "hyperclovax_vision_v2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|minicpm|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -18616,31 +18735,6 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|param2moe|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": "2026-09-20T20:31:51.861026+00:00",
"modelType": "param2moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|zaya|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -18816,56 +18910,6 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|qwen3_5|compressed-tensors": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-20T18:18:38.666148+00:00",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|qwen3_5|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_tokenizer_patch",
"lastTerminalAt": "2026-09-20T17:54:13.170257+00:00",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm|text-generation|deepseek_v4|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -24140,6 +24184,78 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-100|transformers|text-generation|gemma4|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "transformers",
"loadSizeLog2Bucket": 32,
"modelType": "gemma4",
"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
},
"Iluvatar_bi-100|transformers|text-generation|qwen3_5_moe|none|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "transformers",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
},
"Iluvatar_bi-100|transformers|text-generation|qwen3_5|none|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "transformers",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5",
"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
},
"Iluvatar_bi-100|transformers|text-generation|qwen3_vl|none|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -31824,15 +31940,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16134,
"totalRecords": 16315,
"terminalRecords": 16138,
"totalRecords": 16319,
"totals": {
"attributableFailureCount": 5854,
"decisionFailureRate": 0.8616,
"decisionSuccessRate": 0.1384,
"decisionTotal": 6794,
"failureBreakdown": {
"ambiguous_runtime": 3863,
"ambiguous_runtime": 3867,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 102,
@@ -31848,31 +31964,31 @@
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 15194,
"failureRate": 0.9417,
"failureCount": 15198,
"failureRate": 0.9418,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 923,
"successCount": 940,
"successRate": 0.0583,
"total": 16134,
"unresolvedFailureCount": 8417
"successRate": 0.0582,
"total": 16138,
"unresolvedFailureCount": 8421
},
"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。",
@@ -31911,6 +32027,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16315,
"summarizedRecords": 16319,
"version": 1
}