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

state: generation 18477 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-29 17:58:00 +00:00
parent 2c601b6b35
commit dd89cc7a2d
10 changed files with 1660 additions and 1578 deletions
Download Patch File Download Diff File Expand all files Collapse all files

256
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-29T17:16:53.405682+00:00",
"lastSyncTime": "2026-09-29T17:16:53.043636+00:00",
"generatedAt": "2026-09-29T17:54:53.540400+00:00",
"lastSyncTime": "2026-09-29T17:54:53.270754+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -790,6 +790,25 @@
"targetGpu": "Biren_166m",
"taskType": "text-generation"
},
"cambricon_mlu-370-x4|vllm-customized|text-generation|model_type:qwen3_5": {
"architectureSignature": "model_type:qwen3_5",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-22T05:27:11.098010+00:00",
"framework": "vllm-customized",
"latestFailureAt": "2026-09-22T05:27:11.098010+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "qwen3_5",
"sourceModelIds": [
"Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed"
],
"sourceTaskIds": [
"5012909"
],
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation"
},
"cambricon_mlu-370-x4|vllm|text-generation|model_type:lfm2": {
"architectureSignature": "model_type:lfm2",
"architectures": [],
@@ -3285,7 +3304,7 @@
}
},
"architectureCompatibilitySummary": {
"activeBlockCount": 165,
"activeBlockCount": 166,
"byGpuFramework": {
"Ascend_910-b3|vllm": 13,
"Ascend_910-b3|vllm_tokenizer_patch": 5,
@@ -3293,6 +3312,7 @@
"Ascend_910-b4|vllm_tokenizer_patch": 6,
"Biren_166m|vllm": 3,
"Cambricon_mlu-370-x4|vllm": 4,
"Cambricon_mlu-370-x4|vllm-customized": 1,
"Cambricon_mlu-370-x8|vllm": 16,
"Cambricon_mlu-370-x8|vllm-customized": 6,
"Cambricon_mlu-370-x8|vllm-mlu": 5,
@@ -3402,28 +3422,28 @@
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 34,
"decisionFailureRate": 0.8947,
"decisionSuccessRate": 0.1053,
"decisionTotal": 38,
"attributableFailureCount": 35,
"decisionFailureRate": 0.8974,
"decisionSuccessRate": 0.1026,
"decisionTotal": 39,
"failureBreakdown": {
"ambiguous_runtime": 64,
"context_length": 5,
"context_length": 6,
"framework_architecture_unsupported": 28,
"memory_capacity": 1,
"参数/模板问题": 8
},
"failureCount": 106,
"failureRate": 0.9636,
"failureCount": 107,
"failureRate": 0.964,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 4,
"successRate": 0.0364,
"successRate": 0.036,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 110,
"total": 111,
"unresolvedFailureCount": 72
},
"Ascend_910-b3|vllm|text-generation": {
@@ -3837,15 +3857,15 @@
"unresolvedFailureCount": 5
},
"Cambricon_mlu-370-x4|vllm-customized|text-generation": {
"attributableFailureCount": 2,
"attributableFailureCount": 3,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 4,
"framework_architecture_unsupported": 2
"framework_architecture_unsupported": 3
},
"failureCount": 6,
"failureCount": 7,
"failureRate": 1.0,
"framework": "vllm-customized",
"pendingCount": 0,
@@ -3855,7 +3875,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 6,
"total": 7,
"unresolvedFailureCount": 4
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation": {
@@ -6006,26 +6026,26 @@
"unresolvedFailureCount": 1637
},
"vllm-customized": {
"attributableFailureCount": 14,
"attributableFailureCount": 15,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 14,
"decisionTotal": 15,
"failureBreakdown": {
"ambiguous_runtime": 46,
"framework_architecture_unsupported": 10,
"framework_architecture_unsupported": 11,
"model_load": 3,
"platform_infrastructure": 2,
"tokenizer_compatibility": 1,
"参数/模板问题": 5
},
"failureCount": 67,
"failureCount": 68,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 0,
"successRate": 0.0,
"total": 67,
"total": 68,
"unresolvedFailureCount": 51
},
"vllm-mlu": {
@@ -6125,14 +6145,14 @@
"unresolvedFailureCount": 342
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 131,
"decisionFailureRate": 0.9291,
"decisionSuccessRate": 0.0709,
"decisionTotal": 141,
"attributableFailureCount": 132,
"decisionFailureRate": 0.9296,
"decisionSuccessRate": 0.0704,
"decisionTotal": 142,
"failureBreakdown": {
"ambiguous_runtime": 176,
"backend_operator": 15,
"context_length": 5,
"context_length": 6,
"framework_architecture_unsupported": 78,
"memory_capacity": 2,
"model_load": 23,
@@ -6142,27 +6162,27 @@
"tokenizer_compatibility": 2,
"参数/模板问题": 29
},
"failureCount": 338,
"failureCount": 339,
"failureRate": 0.9713,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 10,
"successRate": 0.0287,
"total": 348,
"total": 349,
"unresolvedFailureCount": 205
}
},
"generatedAt": "2026-09-29T17:16:53.391898+00:00",
"generatedAt": "2026-09-29T17:54:53.527997+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 104,
"decisionFailureRate": 0.8254,
"decisionSuccessRate": 0.1746,
"decisionTotal": 126,
"attributableFailureCount": 105,
"decisionFailureRate": 0.8268,
"decisionSuccessRate": 0.1732,
"decisionTotal": 127,
"failureBreakdown": {
"ambiguous_runtime": 130,
"context_length": 5,
"context_length": 6,
"framework_architecture_unsupported": 93,
"memory_capacity": 2,
"repository_structure": 1,
@@ -6171,14 +6191,14 @@
"日志缺失": 3,
"验证失败": 27
},
"failureCount": 303,
"failureRate": 0.9323,
"failureCount": 304,
"failureRate": 0.9325,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 22,
"successRate": 0.0677,
"total": 325,
"successRate": 0.0675,
"total": 326,
"unresolvedFailureCount": 199
},
"Ascend_910-b4": {
@@ -6240,15 +6260,15 @@
"unresolvedFailureCount": 558
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 748,
"decisionFailureRate": 0.9111,
"decisionSuccessRate": 0.0889,
"decisionTotal": 821,
"attributableFailureCount": 749,
"decisionFailureRate": 0.9112,
"decisionSuccessRate": 0.0888,
"decisionTotal": 822,
"failureBreakdown": {
"ambiguous_runtime": 508,
"architecture_compatibility": 53,
"context_length": 48,
"framework_architecture_unsupported": 301,
"framework_architecture_unsupported": 302,
"memory_capacity": 219,
"model_load": 7,
"platform_infrastructure": 16,
@@ -6258,14 +6278,14 @@
"日志缺失": 13,
"验证失败": 42
},
"failureCount": 1614,
"failureRate": 0.9567,
"failureCount": 1615,
"failureRate": 0.9568,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 16,
"successCount": 73,
"successRate": 0.0433,
"total": 1687,
"successRate": 0.0432,
"total": 1688,
"unresolvedFailureCount": 850
},
"Cambricon_mlu-370-x8": {
@@ -6845,15 +6865,15 @@
"unresolvedFailureCount": 6
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 3,
"attributableFailureCount": 4,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 11,
"context_length": 3
"context_length": 4
},
"failureCount": 14,
"failureCount": 15,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "llama",
@@ -6865,7 +6885,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 14,
"total": 15,
"unresolvedFailureCount": 11
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|none": {
@@ -10730,6 +10750,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-customized|text-generation|qwen3_5|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-customized",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-customized|text-generation|stablelm|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -23499,20 +23542,21 @@
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-customized|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-customized",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-27T06:27:28.565882+00:00",
"lastTerminalAt": "2026-09-29T17:54:53.270719+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -23520,7 +23564,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation": {
@@ -24077,9 +24121,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"参数/模板问题": 6
"参数/模板问题": 5
},
"failureCount": 6,
"failureCount": 5,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
@@ -24091,8 +24135,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 6,
"unresolvedFailureCount": 6
"total": 5,
"unresolvedFailureCount": 5
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
"attributableFailureCount": 5,
@@ -24600,6 +24644,31 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-customized|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-customized",
"lastTerminalAt": "2026-09-29T17:54:53.270719+00:00",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -27582,14 +27651,14 @@
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|27": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"context_length": 1
"context_length": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 27,
@@ -27602,7 +27671,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|28": {
@@ -33828,6 +33897,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-customized|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-customized",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-customized|text-generation|stablelm|none|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -52868,20 +52961,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17124,
"totalRecords": 17345,
"terminalRecords": 17126,
"totalRecords": 17347,
"totals": {
"attributableFailureCount": 6136,
"attributableFailureCount": 6138,
"decisionFailureRate": 0.8633,
"decisionSuccessRate": 0.1367,
"decisionTotal": 7108,
"decisionTotal": 7110,
"failureBreakdown": {
"ambiguous_runtime": 4451,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
"context_length": 323,
"framework_architecture_unsupported": 2189,
"context_length": 324,
"framework_architecture_unsupported": 2190,
"memory_capacity": 1206,
"model_load": 550,
"platform_infrastructure": 942,
@@ -52892,14 +52985,14 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16152,
"failureCount": 16154,
"failureRate": 0.9432,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 942,
"successCount": 972,
"successRate": 0.0568,
"total": 17124,
"total": 17126,
"unresolvedFailureCount": 9074
},
"warnings": [
@@ -52929,8 +53022,10 @@
"组合 Kunlunxin_p-800|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 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 Iluvatar_mrv-100|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 Kunlunxin_p-800|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 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 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 Cambricon_mlu-370-x4|vllm-customized|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 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 Mthreads_s4000|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -52953,11 +53048,10 @@
"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 Cambricon_mlu-370-x4|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_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 Vastai_va16|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 Kunlunxin_p-800|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 Vastai_va16|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": 17345,
"summarizedRecords": 17347,
"version": 1
}