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

state: generation 5227 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 15:21:12 +00:00
parent 66b67f877f
commit 3c4aadf900
10 changed files with 2030 additions and 2032 deletions
Download Patch File Download Diff File Expand all files Collapse all files

91
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T15:11:39.016096+00:00",
"lastSyncTime": "2026-09-10T15:11:38.816923+00:00",
"generatedAt": "2026-09-10T15:19:40.193833+00:00",
"lastSyncTime": "2026-09-10T15:19:40.009069+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1866,10 +1866,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 32,
"ambiguous_runtime": 33,
"参数/模板问题": 1
},
"failureCount": 33,
"failureCount": 34,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -1879,8 +1879,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 33,
"unresolvedFailureCount": 33
"total": 34,
"unresolvedFailureCount": 34
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2407,22 +2407,22 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 37,
"failureBreakdown": {
"ambiguous_runtime": 33,
"ambiguous_runtime": 34,
"framework_architecture_unsupported": 4,
"model_load": 1,
"platform_infrastructure": 2,
"tokenizer_compatibility": 32,
"参数/模板问题": 7
},
"failureCount": 79,
"failureCount": 80,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 0,
"successRate": 0.0,
"total": 79,
"unresolvedFailureCount": 40
"total": 80,
"unresolvedFailureCount": 41
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 0,
@@ -2443,7 +2443,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T15:11:39.012071+00:00",
"generatedAt": "2026-09-10T15:19:40.187828+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2634,20 +2634,20 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 64,
"ambiguous_runtime": 65,
"memory_capacity": 1,
"参数/模板问题": 1,
"验证失败": 23
},
"failureCount": 89,
"failureCount": 90,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 89,
"unresolvedFailureCount": 88
"total": 90,
"unresolvedFailureCount": 89
},
"MetaX_c-500": {
"attributableFailureCount": 45,
@@ -3343,9 +3343,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "phi3",
@@ -3357,8 +3357,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 0,
@@ -4114,18 +4114,17 @@
"unresolvedFailureCount": 10
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 14,
"framework_architecture_unsupported": 1,
"tokenizer_compatibility": 1
},
"failureCount": 16,
"failureCount": 15,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
@@ -4137,7 +4136,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 16,
"total": 15,
"unresolvedFailureCount": 14
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
@@ -4305,9 +4304,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 17
"ambiguous_runtime": 18
},
"failureCount": 17,
"failureCount": 18,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
@@ -4319,8 +4318,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 17,
"unresolvedFailureCount": 17
"total": 18,
"unresolvedFailureCount": 18
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -4964,9 +4963,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-10T02:58:51.546388+00:00",
@@ -4979,8 +4978,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 0,
@@ -6097,9 +6096,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 33,
@@ -6112,8 +6111,8 @@
"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|36": {
"attributableFailureCount": 0,
@@ -7122,15 +7121,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1597,
"totalRecords": 1684,
"terminalRecords": 1598,
"totalRecords": 1685,
"totals": {
"attributableFailureCount": 419,
"decisionFailureRate": 0.8915,
"decisionSuccessRate": 0.1085,
"decisionTotal": 470,
"failureBreakdown": {
"ambiguous_runtime": 353,
"ambiguous_runtime": 354,
"backend_operator": 39,
"framework_architecture_unsupported": 272,
"memory_capacity": 11,
@@ -7142,21 +7141,21 @@
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1546,
"failureCount": 1547,
"failureRate": 0.9681,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 51,
"successRate": 0.0319,
"total": 1597,
"unresolvedFailureCount": 1124
"total": 1598,
"unresolvedFailureCount": 1125
},
"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。",
@@ -7164,7 +7163,7 @@
"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。",
@@ -7185,6 +7184,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1684,
"summarizedRecords": 1685,
"version": 1
}