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

state: generation 7446 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-15 00:23:55 +00:00
parent a803753d44
commit d414c168d4
9 changed files with 2209 additions and 2210 deletions
Download Patch File Download Diff File Expand all files Collapse all files

63
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-15T00:03:42.478895+00:00",
"lastSyncTime": "2026-09-15T00:03:42.210393+00:00",
"generatedAt": "2026-09-15T00:22:04.571941+00:00",
"lastSyncTime": "2026-09-15T00:22:04.249561+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2512,14 +2512,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 50,
"failureBreakdown": {
"ambiguous_runtime": 20,
"ambiguous_runtime": 22,
"framework_architecture_unsupported": 38,
"memory_capacity": 1,
"model_load": 5,
"repository_structure": 4,
"runtime_memory": 2
},
"failureCount": 70,
"failureCount": 72,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2529,8 +2529,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 70,
"unresolvedFailureCount": 20
"total": 72,
"unresolvedFailureCount": 22
}
},
"frameworkSummaries": {
@@ -2603,7 +2603,7 @@
"decisionSuccessRate": 0.0122,
"decisionTotal": 329,
"failureBreakdown": {
"ambiguous_runtime": 214,
"ambiguous_runtime": 216,
"backend_operator": 34,
"framework_architecture_unsupported": 236,
"memory_capacity": 7,
@@ -2614,15 +2614,15 @@
"tokenizer_compatibility": 7,
"参数/模板问题": 30
},
"failureCount": 570,
"failureRate": 0.993,
"failureCount": 572,
"failureRate": 0.9931,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 4,
"successRate": 0.007,
"total": 574,
"unresolvedFailureCount": 244
"successRate": 0.0069,
"total": 576,
"unresolvedFailureCount": 246
},
"vllm-mlu": {
"attributableFailureCount": 8,
@@ -2730,7 +2730,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-15T00:03:42.473117+00:00",
"generatedAt": "2026-09-15T00:22:04.564736+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 38,
@@ -3045,7 +3045,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 55,
"failureBreakdown": {
"ambiguous_runtime": 22,
"ambiguous_runtime": 24,
"framework_architecture_unsupported": 43,
"memory_capacity": 1,
"model_load": 5,
@@ -3054,15 +3054,15 @@
"参数/模板问题": 9,
"验证失败": 27
},
"failureCount": 113,
"failureCount": 115,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 113,
"unresolvedFailureCount": 58
"total": 115,
"unresolvedFailureCount": 60
}
},
"observedGpuMemoryGiB": {
@@ -5819,24 +5819,23 @@
"unresolvedFailureCount": 1
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 15,
"consecutiveFailures": 15,
"attributableFailureCount": 14,
"consecutiveFailures": 14,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 15,
"decisionTotal": 14,
"failureBreakdown": {
"ambiguous_runtime": 5,
"ambiguous_runtime": 6,
"framework_architecture_unsupported": 11,
"model_load": 2,
"repository_structure": 1,
"runtime_memory": 1
"repository_structure": 1
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-15T00:03:42.210358+00:00",
"lastTerminalAt": "2026-09-15T00:22:04.249561+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -5845,7 +5844,7 @@
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 5
"unresolvedFailureCount": 6
}
},
"recentProfileCombinationStats": {},
@@ -9011,15 +9010,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1878,
"totalRecords": 1971,
"terminalRecords": 1880,
"totalRecords": 1973,
"totals": {
"attributableFailureCount": 570,
"decisionFailureRate": 0.9005,
"decisionSuccessRate": 0.0995,
"decisionTotal": 633,
"failureBreakdown": {
"ambiguous_runtime": 450,
"ambiguous_runtime": 452,
"backend_operator": 44,
"framework_architecture_unsupported": 365,
"memory_capacity": 12,
@@ -9031,15 +9030,15 @@
"参数/模板问题": 116,
"验证失败": 673
},
"failureCount": 1815,
"failureCount": 1817,
"failureRate": 0.9665,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 6,
"successCount": 63,
"successRate": 0.0335,
"total": 1878,
"unresolvedFailureCount": 1239
"total": 1880,
"unresolvedFailureCount": 1241
},
"warnings": [
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -9077,6 +9076,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1971,
"summarizedRecords": 1973,
"version": 1
}