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

state: generation 10924 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-20 21:33:29 +00:00
parent 1156eef088
commit 61c488c127
9 changed files with 1994 additions and 1897 deletions
Download Patch File Download Diff File Expand all files Collapse all files

300
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-20T21:06:46.570238+00:00",
"lastSyncTime": "2026-09-20T21:06:45.850274+00:00",
"generatedAt": "2026-09-20T21:33:11.597469+00:00",
"lastSyncTime": "2026-09-20T21:33:11.158049+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -310,17 +310,19 @@
"ascend_910-b4|vllm_tokenizer_patch|text-generation|model_type:gemma4": {
"architectureSignature": "model_type:gemma4",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-20T02:52:43.762431+00:00",
"evidenceCount": 2,
"expiresAt": "2026-10-20T02:52:43.765788+00:00",
"framework": "vllm_tokenizer_patch",
"latestFailureAt": "2026-09-20T02:52:43.762431+00:00",
"latestFailureAt": "2026-09-20T02:52:43.765788+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "gemma4",
"sourceModelIds": [
"mlx-community/gemma-4-e2b-it-OptiQ-4bit",
"mlx-community/gemma-4-e4b-it-OptiQ-4bit"
],
"sourceTaskIds": [
"4968997",
"4968999"
],
"targetGpu": "Ascend_910-b4",
@@ -2563,15 +2565,15 @@
"unresolvedFailureCount": 17
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 14,
"attributableFailureCount": 15,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 14,
"decisionTotal": 15,
"failureBreakdown": {
"ambiguous_runtime": 23,
"framework_architecture_unsupported": 14
"ambiguous_runtime": 25,
"framework_architecture_unsupported": 15
},
"failureCount": 37,
"failureCount": 40,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
@@ -2581,8 +2583,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 37,
"unresolvedFailureCount": 23
"total": 40,
"unresolvedFailureCount": 25
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 199,
@@ -4994,28 +4996,28 @@
"unresolvedFailureCount": 137
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 42,
"decisionFailureRate": 0.9545,
"decisionSuccessRate": 0.0455,
"decisionTotal": 44,
"attributableFailureCount": 43,
"decisionFailureRate": 0.9556,
"decisionSuccessRate": 0.0444,
"decisionTotal": 45,
"failureBreakdown": {
"ambiguous_runtime": 35,
"framework_architecture_unsupported": 40,
"ambiguous_runtime": 37,
"framework_architecture_unsupported": 41,
"model_load": 1,
"tokenizer_compatibility": 1
},
"failureCount": 77,
"failureRate": 0.9747,
"failureCount": 80,
"failureRate": 0.9756,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0253,
"total": 79,
"unresolvedFailureCount": 35
"successRate": 0.0244,
"total": 82,
"unresolvedFailureCount": 37
}
},
"generatedAt": "2026-09-20T21:06:46.560057+00:00",
"generatedAt": "2026-09-20T21:33:11.588812+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 81,
@@ -5043,14 +5045,14 @@
"unresolvedFailureCount": 117
},
"Ascend_910-b4": {
"attributableFailureCount": 307,
"decisionFailureRate": 0.832,
"decisionSuccessRate": 0.168,
"decisionTotal": 369,
"attributableFailureCount": 308,
"decisionFailureRate": 0.8324,
"decisionSuccessRate": 0.1676,
"decisionTotal": 370,
"failureBreakdown": {
"ambiguous_runtime": 151,
"ambiguous_runtime": 153,
"context_length": 1,
"framework_architecture_unsupported": 167,
"framework_architecture_unsupported": 168,
"memory_capacity": 18,
"model_load": 85,
"platform_infrastructure": 1,
@@ -5060,15 +5062,15 @@
"日志缺失": 14,
"验证失败": 175
},
"failureCount": 902,
"failureRate": 0.9357,
"failureCount": 905,
"failureRate": 0.9359,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 62,
"successRate": 0.0643,
"total": 964,
"unresolvedFailureCount": 594
"successRate": 0.0641,
"total": 967,
"unresolvedFailureCount": 596
},
"Biren_166m": {
"attributableFailureCount": 176,
@@ -5998,14 +6000,14 @@
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma4|none": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "gemma4",
@@ -6017,7 +6019,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2|none": {
@@ -6026,9 +6028,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
"ambiguous_runtime": 4
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "lfm2",
@@ -6040,8 +6042,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 4,
"unresolvedFailureCount": 4
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|awq": {
"attributableFailureCount": 0,
@@ -6296,6 +6298,29 @@
"total": 8,
"unresolvedFailureCount": 8
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|sophia_hybrid|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "sophia_hybrid",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|spark2_5|fp8": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -12931,17 +12956,17 @@
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 6,
"framework_architecture_unsupported": 2
"ambiguous_runtime": 8,
"framework_architecture_unsupported": 3
},
"failureCount": 8,
"failureCount": 11,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastPlatformFailureAt": null,
@@ -12953,8 +12978,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 8,
"unresolvedFailureCount": 6
"total": 11,
"unresolvedFailureCount": 8
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 6,
@@ -12964,10 +12989,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 5,
"ambiguous_runtime": 4,
"framework_architecture_unsupported": 6
},
"failureCount": 11,
"failureCount": 10,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -12979,8 +13004,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 11,
"unresolvedFailureCount": 5
"total": 10,
"unresolvedFailureCount": 4
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 9,
@@ -13276,18 +13301,18 @@
"unresolvedFailureCount": 1
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 10,
"attributableFailureCount": 9,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.625,
"decisionSuccessRate": 0.375,
"decisionTotal": 16,
"decisionFailureRate": 0.6,
"decisionSuccessRate": 0.4,
"decisionTotal": 15,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 10
"framework_architecture_unsupported": 9
},
"failureCount": 11,
"failureRate": 0.6471,
"failureCount": 10,
"failureRate": 0.625,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-18T11:36:11.987002+00:00",
@@ -13295,10 +13320,10 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 6,
"successRate": 0.3529,
"successRate": 0.375,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 17,
"total": 16,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -13309,9 +13334,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 6
"ambiguous_runtime": 5
},
"failureCount": 6,
"failureCount": 5,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
@@ -13323,8 +13348,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 6,
"unresolvedFailureCount": 6
"total": 5,
"unresolvedFailureCount": 5
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 0,
@@ -14020,18 +14045,18 @@
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma4|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-20T20:49:19.683300+00:00",
"lastTerminalAt": "2026-09-20T21:33:11.157994+00:00",
"modelType": "gemma4",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -14041,7 +14066,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2|none": {
@@ -14051,9 +14076,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-20T18:18:38.666090+00:00",
@@ -14066,8 +14091,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 0,
@@ -14169,6 +14194,31 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|sophia_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_tokenizer_patch",
"lastTerminalAt": "2026-09-20T21:33:11.158049+00:00",
"modelType": "sophia_hybrid",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm|text-generation|gemma3|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -17359,14 +17409,14 @@
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma4|none|32": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 32,
@@ -17379,7 +17429,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2|none|29": {
@@ -17406,6 +17456,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2|none|30": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 30,
"modelType": "lfm2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2|none|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -17838,6 +17912,30 @@
"total": 8,
"unresolvedFailureCount": 8
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|sophia_hybrid|none|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 31,
"modelType": "sophia_hybrid",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|spark2_5|fp8|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -27385,20 +27483,20 @@
"unresolvedFailureCount": 1
}
},
"terminalRecords": 15971,
"totalRecords": 16126,
"terminalRecords": 15974,
"totalRecords": 16129,
"totals": {
"attributableFailureCount": 5804,
"decisionFailureRate": 0.8616,
"decisionSuccessRate": 0.1384,
"decisionTotal": 6736,
"attributableFailureCount": 5805,
"decisionFailureRate": 0.8617,
"decisionSuccessRate": 0.1383,
"decisionTotal": 6737,
"failureBreakdown": {
"ambiguous_runtime": 3810,
"ambiguous_runtime": 3812,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 102,
"context_length": 318,
"framework_architecture_unsupported": 2017,
"framework_architecture_unsupported": 2018,
"memory_capacity": 1196,
"model_load": 484,
"platform_infrastructure": 922,
@@ -27409,15 +27507,15 @@
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 15039,
"failureRate": 0.9416,
"failureCount": 15042,
"failureRate": 0.9417,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 922,
"successCount": 932,
"successRate": 0.0584,
"total": 15971,
"unresolvedFailureCount": 8313
"successRate": 0.0583,
"total": 15974,
"unresolvedFailureCount": 8315
},
"warnings": [
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -27464,12 +27562,12 @@
"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": 16126,
"summarizedRecords": 16129,
"version": 1
}