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

state: generation 4917 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 03:01:00 +00:00
parent b36d182f22
commit 337c98d989
10 changed files with 2349 additions and 2327 deletions
Download Patch File Download Diff File Expand all files Collapse all files

106
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T02:50:12.530651+00:00",
"lastSyncTime": "2026-09-10T02:50:12.317776+00:00",
"generatedAt": "2026-09-10T02:58:51.739711+00:00",
"lastSyncTime": "2026-09-10T02:58:51.546388+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1861,10 +1861,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 21,
"ambiguous_runtime": 22,
"参数/模板问题": 1
},
"failureCount": 22,
"failureCount": 23,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -1874,8 +1874,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 22,
"unresolvedFailureCount": 22
"total": 23,
"unresolvedFailureCount": 23
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2400,22 +2400,22 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 32,
"failureBreakdown": {
"ambiguous_runtime": 22,
"ambiguous_runtime": 23,
"framework_architecture_unsupported": 4,
"model_load": 1,
"platform_infrastructure": 1,
"tokenizer_compatibility": 27,
"参数/模板问题": 7
},
"failureCount": 62,
"failureCount": 63,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"total": 62,
"unresolvedFailureCount": 29
"total": 63,
"unresolvedFailureCount": 30
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 0,
@@ -2436,7 +2436,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T02:50:12.526687+00:00",
"generatedAt": "2026-09-10T02:58:51.735217+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2627,20 +2627,20 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 53,
"ambiguous_runtime": 54,
"memory_capacity": 1,
"参数/模板问题": 1,
"验证失败": 23
},
"failureCount": 78,
"failureCount": 79,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 78,
"unresolvedFailureCount": 77
"total": 79,
"unresolvedFailureCount": 78
},
"MetaX_c-500": {
"attributableFailureCount": 38,
@@ -3291,9 +3291,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "phi3",
@@ -3305,8 +3305,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 0,
@@ -3939,10 +3939,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 11,
"ambiguous_runtime": 10,
"framework_architecture_unsupported": 3
},
"failureCount": 14,
"failureCount": 13,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -3954,8 +3954,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 14,
"unresolvedFailureCount": 11
"total": 13,
"unresolvedFailureCount": 10
},
"Ascend_910-b4|llamacpp|text-generation": {
"attributableFailureCount": 1,
@@ -4303,9 +4303,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 11
"ambiguous_runtime": 12
},
"failureCount": 11,
"failureCount": 12,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
@@ -4317,8 +4317,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 11,
"unresolvedFailureCount": 11
"total": 12,
"unresolvedFailureCount": 12
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -4987,12 +4987,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-09T14:21:21.949411+00:00",
"lastTerminalAt": "2026-09-10T02:58:51.546388+00:00",
"modelType": "phi3",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -5002,8 +5002,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 0,
@@ -5899,6 +5899,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|phi3|compressed-tensors|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 33,
"modelType": "phi3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|36": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -6764,15 +6788,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1490,
"totalRecords": 1574,
"terminalRecords": 1491,
"totalRecords": 1575,
"totals": {
"attributableFailureCount": 394,
"decisionFailureRate": 0.8894,
"decisionSuccessRate": 0.1106,
"decisionTotal": 443,
"failureBreakdown": {
"ambiguous_runtime": 278,
"ambiguous_runtime": 279,
"backend_operator": 25,
"framework_architecture_unsupported": 269,
"memory_capacity": 11,
@@ -6784,21 +6808,21 @@
"参数/模板问题": 94,
"验证失败": 673
},
"failureCount": 1441,
"failureCount": 1442,
"failureRate": 0.9671,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 49,
"successRate": 0.0329,
"total": 1490,
"unresolvedFailureCount": 1045
"total": 1491,
"unresolvedFailureCount": 1046
},
"warnings": [
"GPU Cambricon_mlu-370-x8 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 Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Sunrise_pt-200-x1 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-b4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Vastai_va16 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。",
@@ -6806,7 +6830,7 @@
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x4 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 Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
"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。",
"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 Biren_166m|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -6827,6 +6851,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1574,
"summarizedRecords": 1575,
"version": 1
}