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

state: generation 10941 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-20 22:20:41 +00:00
parent 39171fb0eb
commit e8967ae1c5
8 changed files with 1652 additions and 1651 deletions
Download Patch File Download Diff File Expand all files Collapse all files

103
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-20T22:16:58.735090+00:00",
"lastSyncTime": "2026-09-20T22:16:58.665942+00:00",
"generatedAt": "2026-09-20T22:20:31.772739+00:00",
"lastSyncTime": "2026-09-20T22:20:31.465723+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -4224,10 +4224,10 @@
"unresolvedFailureCount": 158
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 66,
"decisionFailureRate": 0.7674,
"decisionSuccessRate": 0.2326,
"decisionTotal": 86,
"attributableFailureCount": 67,
"decisionFailureRate": 0.7701,
"decisionSuccessRate": 0.2299,
"decisionTotal": 87,
"failureBreakdown": {
"ambiguous_runtime": 59,
"backend_operator": 8,
@@ -4235,21 +4235,21 @@
"memory_capacity": 1,
"model_load": 2,
"repository_structure": 1,
"runtime_memory": 4,
"runtime_memory": 5,
"tokenizer_compatibility": 1,
"参数/模板问题": 12
},
"failureCount": 137,
"failureRate": 0.8726,
"failureCount": 138,
"failureRate": 0.8734,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 20,
"successRate": 0.1274,
"successRate": 0.1266,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 157,
"total": 158,
"unresolvedFailureCount": 71
},
"Mthreads_s4000|vllm|visual-multi-modal": {
@@ -4871,10 +4871,10 @@
"unresolvedFailureCount": 6406
},
"vllm": {
"attributableFailureCount": 3493,
"attributableFailureCount": 3494,
"decisionFailureRate": 0.9768,
"decisionSuccessRate": 0.0232,
"decisionTotal": 3576,
"decisionTotal": 3577,
"failureBreakdown": {
"ambiguous_runtime": 1443,
"architecture_compatibility": 112,
@@ -4886,18 +4886,18 @@
"model_load": 201,
"platform_infrastructure": 864,
"repository_structure": 470,
"runtime_memory": 62,
"runtime_memory": 63,
"tokenizer_compatibility": 409,
"参数/模板问题": 40
},
"failureCount": 5840,
"failureCount": 5841,
"failureRate": 0.986,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 864,
"successCount": 83,
"successRate": 0.014,
"total": 5923,
"total": 5924,
"unresolvedFailureCount": 1483
},
"vllm-customized": {
@@ -5034,7 +5034,7 @@
"unresolvedFailureCount": 37
}
},
"generatedAt": "2026-09-20T22:16:58.725557+00:00",
"generatedAt": "2026-09-20T22:20:31.763393+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 81,
@@ -5331,10 +5331,10 @@
"unresolvedFailureCount": 760
},
"Mthreads_s4000": {
"attributableFailureCount": 70,
"decisionFailureRate": 0.6364,
"decisionSuccessRate": 0.3636,
"decisionTotal": 110,
"attributableFailureCount": 71,
"decisionFailureRate": 0.6396,
"decisionSuccessRate": 0.3604,
"decisionTotal": 111,
"failureBreakdown": {
"ambiguous_runtime": 105,
"backend_operator": 8,
@@ -5342,20 +5342,20 @@
"memory_capacity": 1,
"model_load": 5,
"repository_structure": 1,
"runtime_memory": 4,
"runtime_memory": 5,
"tokenizer_compatibility": 1,
"参数/模板问题": 56,
"日志缺失": 96,
"验证失败": 26
},
"failureCount": 353,
"failureRate": 0.8982,
"failureCount": 354,
"failureRate": 0.8985,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 40,
"successRate": 0.1018,
"total": 393,
"successRate": 0.1015,
"total": 394,
"unresolvedFailureCount": 283
},
"Sunrise_pt-200-x1": {
@@ -13341,18 +13341,18 @@
"unresolvedFailureCount": 1
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 8,
"attributableFailureCount": 7,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.5714,
"decisionSuccessRate": 0.4286,
"decisionTotal": 14,
"decisionFailureRate": 0.5385,
"decisionSuccessRate": 0.4615,
"decisionTotal": 13,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 8
"framework_architecture_unsupported": 7
},
"failureCount": 9,
"failureRate": 0.6,
"failureCount": 8,
"failureRate": 0.5714,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-18T11:36:11.987002+00:00",
@@ -13360,10 +13360,10 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 6,
"successRate": 0.4,
"successRate": 0.4286,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 15,
"total": 14,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -13548,23 +13548,24 @@
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 8,
"consecutiveFailures": 8,
"attributableFailureCount": 9,
"consecutiveFailures": 9,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 8,
"decisionTotal": 9,
"failureBreakdown": {
"ambiguous_runtime": 2,
"backend_operator": 2,
"framework_architecture_unsupported": 5,
"runtime_memory": 1,
"tokenizer_compatibility": 1
},
"failureCount": 10,
"failureCount": 11,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-20T18:36:43.146458+00:00",
"lastTerminalAt": "2026-09-20T22:20:31.465723+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -13572,7 +13573,7 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 10,
"total": 11,
"unresolvedFailureCount": 2
},
"Sunrise_pt-200-x1|unknown|text-generation": {
@@ -27573,13 +27574,13 @@
"unresolvedFailureCount": 1
}
},
"terminalRecords": 15976,
"totalRecords": 16132,
"terminalRecords": 15977,
"totalRecords": 16133,
"totals": {
"attributableFailureCount": 5806,
"attributableFailureCount": 5807,
"decisionFailureRate": 0.8617,
"decisionSuccessRate": 0.1383,
"decisionTotal": 6738,
"decisionTotal": 6739,
"failureBreakdown": {
"ambiguous_runtime": 3812,
"architecture_compatibility": 212,
@@ -27591,20 +27592,20 @@
"model_load": 484,
"platform_infrastructure": 922,
"repository_structure": 734,
"runtime_memory": 82,
"runtime_memory": 83,
"tokenizer_compatibility": 658,
"参数/模板问题": 3112,
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 15044,
"failureCount": 15045,
"failureRate": 0.9417,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 922,
"successCount": 932,
"successRate": 0.0583,
"total": 15976,
"total": 15977,
"unresolvedFailureCount": 8316
},
"warnings": [
@@ -27652,12 +27653,12 @@
"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": 16132,
"summarizedRecords": 16133,
"version": 1
}