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

state: generation 9943 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-19 18:07:54 +00:00
parent 0782c54257
commit 3ab195df6a
9 changed files with 1799 additions and 1778 deletions
Download Patch File Download Diff File Expand all files Collapse all files

104
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-19T17:55:07.167462+00:00",
"lastSyncTime": "2026-09-19T17:55:06.900814+00:00",
"generatedAt": "2026-09-19T18:05:32.126342+00:00",
"lastSyncTime": "2026-09-19T18:05:32.091140+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2531,9 +2531,9 @@
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 53,
"decisionFailureRate": 0.7794,
"decisionSuccessRate": 0.2206,
"decisionTotal": 68,
"decisionFailureRate": 0.7681,
"decisionSuccessRate": 0.2319,
"decisionTotal": 69,
"failureBreakdown": {
"ambiguous_runtime": 46,
"backend_operator": 6,
@@ -2546,16 +2546,16 @@
"参数/模板问题": 12
},
"failureCount": 111,
"failureRate": 0.881,
"failureRate": 0.874,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 15,
"successRate": 0.119,
"successCount": 16,
"successRate": 0.126,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 126,
"total": 127,
"unresolvedFailureCount": 58
},
"Sunrise_pt-200-x1|unknown|text-generation": {
@@ -2863,9 +2863,9 @@
},
"vllm": {
"attributableFailureCount": 428,
"decisionFailureRate": 0.8629,
"decisionSuccessRate": 0.1371,
"decisionTotal": 496,
"decisionFailureRate": 0.8612,
"decisionSuccessRate": 0.1388,
"decisionTotal": 497,
"failureBreakdown": {
"ambiguous_runtime": 247,
"backend_operator": 40,
@@ -2879,13 +2879,13 @@
"参数/模板问题": 40
},
"failureCount": 717,
"failureRate": 0.9134,
"failureRate": 0.9122,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 68,
"successRate": 0.0866,
"total": 785,
"successCount": 69,
"successRate": 0.0878,
"total": 786,
"unresolvedFailureCount": 287
},
"vllm-mlu": {
@@ -2998,7 +2998,7 @@
"unresolvedFailureCount": 21
}
},
"generatedAt": "2026-09-19T17:55:07.162208+00:00",
"generatedAt": "2026-09-19T18:05:32.120893+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 62,
@@ -3237,9 +3237,9 @@
},
"Mthreads_s4000": {
"attributableFailureCount": 54,
"decisionFailureRate": 0.7606,
"decisionSuccessRate": 0.2394,
"decisionTotal": 71,
"decisionFailureRate": 0.75,
"decisionSuccessRate": 0.25,
"decisionTotal": 72,
"failureBreakdown": {
"ambiguous_runtime": 46,
"backend_operator": 6,
@@ -3253,13 +3253,13 @@
"验证失败": 26
},
"failureCount": 146,
"failureRate": 0.8957,
"failureRate": 0.8902,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 17,
"successRate": 0.1043,
"total": 163,
"successCount": 18,
"successRate": 0.1098,
"total": 164,
"unresolvedFailureCount": 92
},
"Sunrise_pt-200-x1": {
@@ -7075,23 +7075,23 @@
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 4,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 2
},
"failureCount": 2,
"failureRate": 0.3333,
"failureRate": 0.2857,
"framework": "vllm",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 4,
"successRate": 0.6667,
"successCount": 5,
"successRate": 0.7143,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 6,
"total": 7,
"unresolvedFailureCount": 2
},
"Mthreads_s4000|vllm|text-generation|llama|none": {
@@ -14674,6 +14674,28 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|llama|awq|30": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm",
"loadSizeLog2Bucket": 30,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|llama|awq|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -16062,13 +16084,13 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2353,
"totalRecords": 2456,
"terminalRecords": 2354,
"totalRecords": 2457,
"totals": {
"attributableFailureCount": 771,
"decisionFailureRate": 0.8159,
"decisionSuccessRate": 0.1841,
"decisionTotal": 945,
"decisionFailureRate": 0.815,
"decisionSuccessRate": 0.185,
"decisionTotal": 946,
"failureBreakdown": {
"ambiguous_runtime": 591,
"backend_operator": 55,
@@ -16083,17 +16105,17 @@
"验证失败": 673
},
"failureCount": 2179,
"failureRate": 0.9261,
"failureRate": 0.9257,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 11,
"successCount": 174,
"successRate": 0.0739,
"total": 2353,
"successCount": 175,
"successRate": 0.0743,
"total": 2354,
"unresolvedFailureCount": 1397
},
"warnings": [
"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。",
"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。",
@@ -16104,7 +16126,7 @@
"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 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。",
"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。",
@@ -16129,6 +16151,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2456,
"summarizedRecords": 2457,
"version": 1
}