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

state: generation 10667 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-20 15:25:40 +00:00
parent cd17eab253
commit 8ae0521510
10 changed files with 1954 additions and 1897 deletions
Download Patch File Download Diff File Expand all files Collapse all files

201
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-20T15:22:01.735347+00:00",
"lastSyncTime": "2026-09-20T15:22:01.055014+00:00",
"generatedAt": "2026-09-20T15:25:29.241097+00:00",
"lastSyncTime": "2026-09-20T15:25:28.950050+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -529,6 +529,25 @@
"targetGpu": "Biren_166m",
"taskType": "text-generation"
},
"biren_166m|vllm|text-generation|model_type:nemotron_h": {
"architectureSignature": "model_type:nemotron_h",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-20T03:41:49.061655+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-20T03:41:49.061655+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "nemotron_h",
"sourceModelIds": [
"nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4"
],
"sourceTaskIds": [
"4970007"
],
"targetGpu": "Biren_166m",
"taskType": "text-generation"
},
"cambricon_mlu-370-x8|vllm-mlu|text-generation|model_type:nemotron_h": {
"architectureSignature": "model_type:nemotron_h",
"architectures": [],
@@ -1940,12 +1959,12 @@
}
},
"architectureCompatibilitySummary": {
"activeBlockCount": 94,
"activeBlockCount": 95,
"byGpuFramework": {
"Ascend_910-b3|vllm": 11,
"Ascend_910-b3|vllm_tokenizer_patch": 1,
"Ascend_910-b4|vllm": 12,
"Biren_166m|vllm": 1,
"Biren_166m|vllm": 2,
"Cambricon_mlu-370-x8|vllm": 2,
"Cambricon_mlu-370-x8|vllm-mlu": 5,
"Iluvatar_bi-150|transformers": 2,
@@ -2354,27 +2373,27 @@
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 34,
"decisionFailureRate": 0.6939,
"decisionSuccessRate": 0.3061,
"decisionTotal": 49,
"attributableFailureCount": 35,
"decisionFailureRate": 0.7,
"decisionSuccessRate": 0.3,
"decisionTotal": 50,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 26,
"framework_architecture_unsupported": 27,
"model_load": 7,
"tokenizer_compatibility": 1
},
"failureCount": 35,
"failureRate": 0.7,
"failureCount": 36,
"failureRate": 0.7059,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 15,
"successRate": 0.3,
"successRate": 0.2941,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 50,
"total": 51,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -4452,17 +4471,17 @@
"unresolvedFailureCount": 6405
},
"vllm": {
"attributableFailureCount": 3474,
"attributableFailureCount": 3475,
"decisionFailureRate": 0.9778,
"decisionSuccessRate": 0.0222,
"decisionTotal": 3553,
"decisionTotal": 3554,
"failureBreakdown": {
"ambiguous_runtime": 1434,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
"context_length": 161,
"framework_architecture_unsupported": 1260,
"framework_architecture_unsupported": 1261,
"memory_capacity": 720,
"model_load": 198,
"platform_infrastructure": 864,
@@ -4471,14 +4490,14 @@
"tokenizer_compatibility": 408,
"参数/模板问题": 40
},
"failureCount": 5812,
"failureCount": 5813,
"failureRate": 0.9866,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 864,
"successCount": 79,
"successRate": 0.0134,
"total": 5891,
"total": 5892,
"unresolvedFailureCount": 1474
},
"vllm-customized": {
@@ -4612,7 +4631,7 @@
"unresolvedFailureCount": 24
}
},
"generatedAt": "2026-09-20T15:22:01.726831+00:00",
"generatedAt": "2026-09-20T15:25:29.233684+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 75,
@@ -4668,15 +4687,15 @@
"unresolvedFailureCount": 588
},
"Biren_166m": {
"attributableFailureCount": 172,
"decisionFailureRate": 0.8731,
"decisionSuccessRate": 0.1269,
"decisionTotal": 197,
"attributableFailureCount": 173,
"decisionFailureRate": 0.8737,
"decisionSuccessRate": 0.1263,
"decisionTotal": 198,
"failureBreakdown": {
"ambiguous_runtime": 131,
"backend_operator": 4,
"context_length": 10,
"framework_architecture_unsupported": 113,
"framework_architecture_unsupported": 114,
"memory_capacity": 1,
"model_load": 18,
"platform_infrastructure": 2,
@@ -4687,14 +4706,14 @@
"日志缺失": 62,
"验证失败": 27
},
"failureCount": 608,
"failureRate": 0.9605,
"failureCount": 609,
"failureRate": 0.9606,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 25,
"successRate": 0.0395,
"total": 633,
"successRate": 0.0394,
"total": 634,
"unresolvedFailureCount": 434
},
"Cambricon_mlu-370-x4": {
@@ -5843,6 +5862,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|nemotron_h|modelopt": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "nemotron_h",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|plamo3|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -11242,28 +11284,28 @@
"unresolvedFailureCount": 5
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 1,
"consecutiveFailures": 0,
"attributableFailureCount": 2,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.5,
"decisionSuccessRate": 0.5,
"decisionTotal": 2,
"decisionFailureRate": 0.6667,
"decisionSuccessRate": 0.3333,
"decisionTotal": 3,
"failureBreakdown": {
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 1,
"failureRate": 0.5,
"failureCount": 2,
"failureRate": 0.6667,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-20T14:32:15.260751+00:00",
"lastTerminalAt": "2026-09-20T15:25:28.950050+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.5,
"successRate": 0.3333,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -11666,18 +11708,18 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 2,
"failureBreakdown": {
"backend_operator": 1,
"framework_architecture_unsupported": 2,
"framework_architecture_unsupported": 1,
"platform_infrastructure": 1
},
"failureCount": 4,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": "2026-09-15T06:15:21+00:00",
@@ -11689,7 +11731,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 4,
"total": 3,
"unresolvedFailureCount": 0
},
"Vastai_va16|unknown|text-generation": {
@@ -11922,6 +11964,31 @@
"total": 3,
"unresolvedFailureCount": 3
},
"Biren_166m|vllm|text-generation|nemotron_h|modelopt": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-20T15:25:28.950050+00:00",
"modelType": "nemotron_h",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -14342,6 +14409,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|nemotron_h|modelopt|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "nemotron_h",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|plamo3|none|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -22314,20 +22405,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 15876,
"totalRecords": 15981,
"terminalRecords": 15877,
"totalRecords": 15982,
"totals": {
"attributableFailureCount": 5755,
"attributableFailureCount": 5756,
"decisionFailureRate": 0.8613,
"decisionSuccessRate": 0.1387,
"decisionTotal": 6682,
"decisionTotal": 6683,
"failureBreakdown": {
"ambiguous_runtime": 3770,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 102,
"context_length": 318,
"framework_architecture_unsupported": 1985,
"framework_architecture_unsupported": 1986,
"memory_capacity": 1195,
"model_load": 478,
"platform_infrastructure": 922,
@@ -22338,14 +22429,14 @@
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 14949,
"failureCount": 14950,
"failureRate": 0.9416,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 922,
"successCount": 927,
"successRate": 0.0584,
"total": 15876,
"total": 15877,
"unresolvedFailureCount": 8272
},
"warnings": [
@@ -22391,12 +22482,12 @@
"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": 15981,
"summarizedRecords": 15982,
"version": 1
}