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

state: generation 9948 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-19 18:17:34 +00:00
parent d6e16acecc
commit c5e930ad48
9 changed files with 1758 additions and 1735 deletions
Download Patch File Download Diff File Expand all files Collapse all files

84
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-19T18:05:32.126342+00:00",
"lastSyncTime": "2026-09-19T18:05:32.091140+00:00",
"generatedAt": "2026-09-19T18:15:14.182850+00:00",
"lastSyncTime": "2026-09-19T18:15:13.897248+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1927,10 +1927,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 9,
"failureBreakdown": {
"ambiguous_runtime": 15,
"ambiguous_runtime": 16,
"framework_architecture_unsupported": 9
},
"failureCount": 24,
"failureCount": 25,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
@@ -1940,8 +1940,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 24,
"unresolvedFailureCount": 15
"total": 25,
"unresolvedFailureCount": 16
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 58,
@@ -2984,21 +2984,21 @@
"decisionSuccessRate": 0.0455,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 21,
"ambiguous_runtime": 22,
"framework_architecture_unsupported": 21
},
"failureCount": 42,
"failureRate": 0.9767,
"failureCount": 43,
"failureRate": 0.9773,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0233,
"total": 43,
"unresolvedFailureCount": 21
"successRate": 0.0227,
"total": 44,
"unresolvedFailureCount": 22
}
},
"generatedAt": "2026-09-19T18:05:32.120893+00:00",
"generatedAt": "2026-09-19T18:15:14.177520+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 62,
@@ -3029,7 +3029,7 @@
"decisionSuccessRate": 0.0286,
"decisionTotal": 70,
"failureBreakdown": {
"ambiguous_runtime": 58,
"ambiguous_runtime": 59,
"framework_architecture_unsupported": 63,
"memory_capacity": 1,
"model_load": 1,
@@ -3038,15 +3038,15 @@
"参数/模板问题": 13,
"验证失败": 175
},
"failureCount": 314,
"failureCount": 315,
"failureRate": 0.9937,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0063,
"total": 316,
"unresolvedFailureCount": 246
"total": 317,
"unresolvedFailureCount": 247
},
"Biren_166m": {
"attributableFailureCount": 69,
@@ -3702,9 +3702,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "llama",
@@ -3716,8 +3716,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|none": {
"attributableFailureCount": 0,
@@ -9328,6 +9328,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|awq|30": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 30,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|awq|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -16084,15 +16108,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2354,
"totalRecords": 2457,
"terminalRecords": 2355,
"totalRecords": 2458,
"totals": {
"attributableFailureCount": 771,
"decisionFailureRate": 0.815,
"decisionSuccessRate": 0.185,
"decisionTotal": 946,
"failureBreakdown": {
"ambiguous_runtime": 591,
"ambiguous_runtime": 592,
"backend_operator": 55,
"framework_architecture_unsupported": 519,
"memory_capacity": 12,
@@ -16104,18 +16128,18 @@
"参数/模板问题": 133,
"验证失败": 673
},
"failureCount": 2179,
"failureCount": 2180,
"failureRate": 0.9257,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 11,
"successCount": 175,
"successRate": 0.0743,
"total": 2354,
"unresolvedFailureCount": 1397
"total": 2355,
"unresolvedFailureCount": 1398
},
"warnings": [
"GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -16126,7 +16150,7 @@
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
"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 Ascend_910-b4|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 Iluvatar_mrv-100|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -16151,6 +16175,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2457,
"summarizedRecords": 2458,
"version": 1
}