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

state: generation 5998 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-12 03:16:47 +00:00
parent 687289b55c
commit 8995d74bdf
9 changed files with 2085 additions and 2036 deletions
Download Patch File Download Diff File Expand all files Collapse all files

110
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-12T03:05:48.188591+00:00",
"lastSyncTime": "2026-09-12T03:05:47.937930+00:00",
"generatedAt": "2026-09-12T03:14:58.686149+00:00",
"lastSyncTime": "2026-09-12T03:14:58.435392+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2101,17 +2101,18 @@
"unresolvedFailureCount": 33
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 42,
"attributableFailureCount": 43,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 42,
"decisionTotal": 43,
"failureBreakdown": {
"backend_operator": 1,
"framework_architecture_unsupported": 4,
"platform_infrastructure": 2,
"tokenizer_compatibility": 38,
"参数/模板问题": 6
},
"failureCount": 50,
"failureCount": 51,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -2121,7 +2122,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 50,
"total": 51,
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -2461,26 +2462,27 @@
"unresolvedFailureCount": 4
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 45,
"attributableFailureCount": 46,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 45,
"decisionTotal": 46,
"failureBreakdown": {
"ambiguous_runtime": 36,
"backend_operator": 1,
"framework_architecture_unsupported": 6,
"model_load": 1,
"platform_infrastructure": 2,
"tokenizer_compatibility": 38,
"参数/模板问题": 7
},
"failureCount": 90,
"failureCount": 91,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 0,
"successRate": 0.0,
"total": 90,
"total": 91,
"unresolvedFailureCount": 43
},
"vllm_tokenizer_patch": {
@@ -2502,7 +2504,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T03:05:48.184736+00:00",
"generatedAt": "2026-09-12T03:14:58.681095+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2760,26 +2762,27 @@
"unresolvedFailureCount": 77
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 46,
"decisionFailureRate": 0.9787,
"decisionSuccessRate": 0.0213,
"decisionTotal": 47,
"attributableFailureCount": 47,
"decisionFailureRate": 0.9792,
"decisionSuccessRate": 0.0208,
"decisionTotal": 48,
"failureBreakdown": {
"ambiguous_runtime": 1,
"backend_operator": 1,
"framework_architecture_unsupported": 5,
"platform_infrastructure": 3,
"tokenizer_compatibility": 41,
"参数/模板问题": 9,
"验证失败": 32
},
"failureCount": 91,
"failureRate": 0.9891,
"failureCount": 92,
"failureRate": 0.9892,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 1,
"successRate": 0.0109,
"total": 92,
"successRate": 0.0108,
"total": 93,
"unresolvedFailureCount": 42
},
"Vastai_va16": {
@@ -3972,6 +3975,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"backend_operator": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -6946,6 +6972,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|31": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"backend_operator": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 31,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -7187,16 +7237,16 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1682,
"totalRecords": 1769,
"terminalRecords": 1683,
"totalRecords": 1770,
"totals": {
"attributableFailureCount": 454,
"decisionFailureRate": 0.8902,
"decisionSuccessRate": 0.1098,
"decisionTotal": 510,
"attributableFailureCount": 455,
"decisionFailureRate": 0.8904,
"decisionSuccessRate": 0.1096,
"decisionTotal": 511,
"failureBreakdown": {
"ambiguous_runtime": 394,
"backend_operator": 40,
"backend_operator": 41,
"framework_architecture_unsupported": 280,
"memory_capacity": 11,
"model_load": 65,
@@ -7207,21 +7257,20 @@
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1626,
"failureCount": 1627,
"failureRate": 0.9667,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 56,
"successRate": 0.0333,
"total": 1682,
"total": 1683,
"unresolvedFailureCount": 1168
},
"warnings": [
"GPU Ascend_910-b3 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 Mthreads_s4000 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 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 Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -7230,6 +7279,7 @@
"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。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
"组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 hygon_k100-ai|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|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -7251,6 +7301,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1769,
"summarizedRecords": 1770,
"version": 1
}