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

state: generation 11540 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-21 15:54:39 +00:00
parent 426025eb1a
commit cd3ab70ece
9 changed files with 1762 additions and 1767 deletions
Download Patch File Download Diff File Expand all files Collapse all files

122
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T15:17:58.482139+00:00",
"lastSyncTime": "2026-09-21T15:17:58.391613+00:00",
"generatedAt": "2026-09-21T15:54:38.201498+00:00",
"lastSyncTime": "2026-09-21T15:54:37.859039+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1206,7 +1206,7 @@
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|model_type:gemma4": {
"architectureSignature": "model_type:gemma4",
"architectures": [],
"evidenceCount": 2,
"evidenceCount": 1,
"expiresAt": "2026-10-20T03:41:49.472121+00:00",
"framework": "vllm-patch-tokenizer",
"latestFailureAt": "2026-09-20T03:41:49.472121+00:00",
@@ -1214,12 +1214,10 @@
"matchType": "model_type",
"modelType": "gemma4",
"sourceModelIds": [
"mlx-community/gemma-4-e2b-it-OptiQ-4bit",
"mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit"
"mlx-community/gemma-4-e2b-it-OptiQ-4bit"
],
"sourceTaskIds": [
"4970033",
"4969662"
"4970033"
],
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation"
@@ -3189,23 +3187,23 @@
"decisionSuccessRate": 0.2632,
"decisionTotal": 57,
"failureBreakdown": {
"ambiguous_runtime": 10,
"ambiguous_runtime": 11,
"framework_architecture_unsupported": 29,
"model_load": 11,
"tokenizer_compatibility": 2
},
"failureCount": 52,
"failureRate": 0.7761,
"failureCount": 53,
"failureRate": 0.7794,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 15,
"successRate": 0.2239,
"successRate": 0.2206,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 67,
"unresolvedFailureCount": 10
"total": 68,
"unresolvedFailureCount": 11
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 695,
@@ -5388,7 +5386,7 @@
"decisionSuccessRate": 0.0243,
"decisionTotal": 3619,
"failureBreakdown": {
"ambiguous_runtime": 1485,
"ambiguous_runtime": 1486,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
@@ -5402,15 +5400,15 @@
"tokenizer_compatibility": 411,
"参数/模板问题": 45
},
"failureCount": 5926,
"failureCount": 5927,
"failureRate": 0.9854,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 865,
"successCount": 88,
"successRate": 0.0146,
"total": 6014,
"unresolvedFailureCount": 1530
"total": 6015,
"unresolvedFailureCount": 1531
},
"vllm-customized": {
"attributableFailureCount": 4,
@@ -5556,7 +5554,7 @@
"unresolvedFailureCount": 91
}
},
"generatedAt": "2026-09-21T15:17:58.471978+00:00",
"generatedAt": "2026-09-21T15:54:38.191412+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 95,
@@ -5618,7 +5616,7 @@
"decisionSuccessRate": 0.1202,
"decisionTotal": 208,
"failureBreakdown": {
"ambiguous_runtime": 162,
"ambiguous_runtime": 163,
"backend_operator": 4,
"context_length": 10,
"framework_architecture_unsupported": 117,
@@ -5632,15 +5630,15 @@
"日志缺失": 62,
"验证失败": 27
},
"failureCount": 650,
"failureCount": 651,
"failureRate": 0.963,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 25,
"successRate": 0.037,
"total": 675,
"unresolvedFailureCount": 465
"total": 676,
"unresolvedFailureCount": 466
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 716,
@@ -7929,9 +7927,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "llama",
@@ -7943,8 +7941,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Biren_166m|vllm|text-generation|llama|none": {
"attributableFailureCount": 1,
@@ -16504,16 +16502,16 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 7,
"ambiguous_runtime": 8,
"framework_architecture_unsupported": 2,
"model_load": 4,
"tokenizer_compatibility": 1
},
"failureCount": 14,
"failureCount": 15,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T05:07:16.468545+00:00",
"lastTerminalAt": "2026-09-21T15:54:37.859021+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -16521,8 +16519,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 14,
"unresolvedFailureCount": 7
"total": 15,
"unresolvedFailureCount": 8
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -17070,17 +17068,17 @@
"unresolvedFailureCount": 9
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 2,
"framework_architecture_unsupported": 1,
"repository_structure": 1
},
"failureCount": 3,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"lastPlatformFailureAt": null,
@@ -17092,7 +17090,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 3,
"total": 2,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm|text-generation": {
@@ -17534,12 +17532,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-21T01:08:25.664308+00:00",
"lastTerminalAt": "2026-09-21T15:54:37.859021+00:00",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -17549,8 +17547,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Biren_166m|vllm|text-generation|mistral|compressed-tensors": {
"attributableFailureCount": 1,
@@ -20384,15 +20382,15 @@
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|gemma4|none": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 2
"framework_architecture_unsupported": 1
},
"failureCount": 2,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"lastTerminalAt": "2026-09-21T14:32:55.759813+00:00",
@@ -20405,7 +20403,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 2,
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|mpt|none": {
@@ -23385,9 +23383,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
@@ -23400,8 +23398,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Biren_166m|vllm|text-generation|llama|none|30": {
"attributableFailureCount": 1,
@@ -35435,15 +35433,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16302,
"totalRecords": 16490,
"terminalRecords": 16303,
"totalRecords": 16491,
"totals": {
"attributableFailureCount": 5890,
"decisionFailureRate": 0.8616,
"decisionSuccessRate": 0.1384,
"decisionTotal": 6836,
"failureBreakdown": {
"ambiguous_runtime": 3959,
"ambiguous_runtime": 3960,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 103,
@@ -35459,31 +35457,31 @@
"日志缺失": 719,
"验证失败": 674
},
"failureCount": 15356,
"failureCount": 15357,
"failureRate": 0.942,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 925,
"successCount": 946,
"successRate": 0.058,
"total": 16302,
"unresolvedFailureCount": 8541
"total": 16303,
"unresolvedFailureCount": 8542
},
"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 Vastai_va16 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。",
"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。",
@@ -35523,6 +35521,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16490,
"summarizedRecords": 16491,
"version": 1
}