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

state: generation 9357 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-18 16:33:18 +00:00
parent ed8d5d1685
commit f51fae4e13
9 changed files with 1922 additions and 1920 deletions
Download Patch File Download Diff File Expand all files Collapse all files

136
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-18T16:05:24.226942+00:00",
"lastSyncTime": "2026-09-18T16:05:24.190526+00:00",
"generatedAt": "2026-09-18T16:31:25.872973+00:00",
"lastSyncTime": "2026-09-18T16:31:25.093497+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2031,21 +2031,21 @@
"decisionSuccessRate": 0.625,
"decisionTotal": 8,
"failureBreakdown": {
"ambiguous_runtime": 7,
"ambiguous_runtime": 8,
"framework_architecture_unsupported": 3
},
"failureCount": 10,
"failureRate": 0.6667,
"failureCount": 11,
"failureRate": 0.6875,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 5,
"successRate": 0.3333,
"successRate": 0.3125,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 15,
"unresolvedFailureCount": 7
"total": 16,
"unresolvedFailureCount": 8
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 8,
@@ -2639,22 +2639,22 @@
"decisionSuccessRate": 0.2,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 5,
"ambiguous_runtime": 6,
"framework_architecture_unsupported": 3,
"model_load": 1
},
"failureCount": 9,
"failureRate": 0.9,
"failureCount": 10,
"failureRate": 0.9091,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.1,
"successRate": 0.0909,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 10,
"unresolvedFailureCount": 5
"total": 11,
"unresolvedFailureCount": 6
},
"Vastai_va16|vllm|text-generation": {
"attributableFailureCount": 58,
@@ -2873,20 +2873,20 @@
"decisionSuccessRate": 0.52,
"decisionTotal": 25,
"failureBreakdown": {
"ambiguous_runtime": 37,
"ambiguous_runtime": 38,
"framework_architecture_unsupported": 11,
"tokenizer_compatibility": 1,
"参数/模板问题": 3
},
"failureCount": 52,
"failureRate": 0.8,
"failureCount": 53,
"failureRate": 0.803,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.2,
"total": 65,
"unresolvedFailureCount": 40
"successRate": 0.197,
"total": 66,
"unresolvedFailureCount": 41
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 13,
@@ -2939,7 +2939,7 @@
"decisionSuccessRate": 0.0149,
"decisionTotal": 67,
"failureBreakdown": {
"ambiguous_runtime": 73,
"ambiguous_runtime": 74,
"backend_operator": 7,
"framework_architecture_unsupported": 10,
"model_load": 1,
@@ -2947,15 +2947,15 @@
"tokenizer_compatibility": 48,
"参数/模板问题": 8
},
"failureCount": 155,
"failureCount": 156,
"failureRate": 0.9936,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 8,
"successCount": 1,
"successRate": 0.0064,
"total": 156,
"unresolvedFailureCount": 81
"total": 157,
"unresolvedFailureCount": 82
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 14,
@@ -2977,7 +2977,7 @@
"unresolvedFailureCount": 18
}
},
"generatedAt": "2026-09-18T16:05:24.221694+00:00",
"generatedAt": "2026-09-18T16:31:25.867509+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 58,
@@ -3059,22 +3059,22 @@
"decisionSuccessRate": 0.2143,
"decisionTotal": 42,
"failureBreakdown": {
"ambiguous_runtime": 46,
"ambiguous_runtime": 47,
"framework_architecture_unsupported": 30,
"memory_capacity": 1,
"tokenizer_compatibility": 2,
"参数/模板问题": 1,
"验证失败": 39
},
"failureCount": 119,
"failureRate": 0.9297,
"failureCount": 120,
"failureRate": 0.9302,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 9,
"successRate": 0.0703,
"total": 128,
"unresolvedFailureCount": 86
"successRate": 0.0698,
"total": 129,
"unresolvedFailureCount": 87
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 20,
@@ -3272,22 +3272,22 @@
"decisionSuccessRate": 0.2346,
"decisionTotal": 81,
"failureBreakdown": {
"ambiguous_runtime": 79,
"ambiguous_runtime": 80,
"framework_architecture_unsupported": 55,
"memory_capacity": 1,
"model_load": 6,
"参数/模板问题": 15,
"验证失败": 130
},
"failureCount": 286,
"failureRate": 0.9377,
"failureCount": 287,
"failureRate": 0.9379,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 19,
"successRate": 0.0623,
"total": 305,
"unresolvedFailureCount": 224
"successRate": 0.0621,
"total": 306,
"unresolvedFailureCount": 225
},
"hygon_k100-ai": {
"attributableFailureCount": 69,
@@ -4276,9 +4276,11 @@
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 5,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 0.1667,
"framework": "vllm-mlu",
"modelType": "qwen3",
"pendingCount": 0,
@@ -4286,11 +4288,11 @@
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 5,
"successRate": 1.0,
"successRate": 0.8333,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 0
"total": 6,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|fp8": {
"attributableFailureCount": 0,
@@ -7120,9 +7122,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 4
"ambiguous_runtime": 5
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "llama",
@@ -7134,8 +7136,8 @@
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 4
"total": 5,
"unresolvedFailureCount": 5
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|minicpm|none": {
"attributableFailureCount": 0,
@@ -9519,9 +9521,11 @@
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 5,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 0.1667,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 32,
"modelType": "qwen3",
@@ -9530,11 +9534,11 @@
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 5,
"successRate": 1.0,
"successRate": 0.8333,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 0
"total": 6,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|fp8|32": {
"attributableFailureCount": 0,
@@ -14074,9 +14078,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
"ambiguous_runtime": 4
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 32,
@@ -14089,8 +14093,8 @@
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 4,
"unresolvedFailureCount": 4
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|llama|awq|33": {
"attributableFailureCount": 0,
@@ -14549,15 +14553,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2264,
"totalRecords": 2367,
"terminalRecords": 2266,
"totalRecords": 2369,
"totals": {
"attributableFailureCount": 736,
"decisionFailureRate": 0.8373,
"decisionSuccessRate": 0.1627,
"decisionTotal": 879,
"failureBreakdown": {
"ambiguous_runtime": 568,
"ambiguous_runtime": 570,
"backend_operator": 55,
"framework_architecture_unsupported": 487,
"memory_capacity": 12,
@@ -14569,15 +14573,15 @@
"参数/模板问题": 133,
"验证失败": 673
},
"failureCount": 2121,
"failureRate": 0.9368,
"failureCount": 2123,
"failureRate": 0.9369,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 11,
"successCount": 143,
"successRate": 0.0632,
"total": 2264,
"unresolvedFailureCount": 1374
"successRate": 0.0631,
"total": 2266,
"unresolvedFailureCount": 1376
},
"warnings": [
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -14616,6 +14620,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2367,
"summarizedRecords": 2369,
"version": 1
}