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

state: generation 11903 (cycle_no_slots)

Browse Source
This commit is contained in:
CoolBoy
2026-09-21 23:35:26 +00:00
parent 0deebb678a
commit c3d876419d
6 changed files with 1663 additions and 1617 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -2869,7 +2869,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-21T23:33:41.859025+00:00",
"generatedAt": "2026-09-21T23:35:11.001898+00:00",
"summary": {
"activeBlockCount": 144,
"byGpuFramework": {

109
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T23:30:30.170990+00:00",
"lastSyncTime": "2026-09-21T23:30:29.669131+00:00",
"generatedAt": "2026-09-21T23:35:10.930892+00:00",
"lastSyncTime": "2026-09-21T23:35:10.664127+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -5347,19 +5347,19 @@
"unresolvedFailureCount": 72
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
"attributableFailureCount": 31,
"attributableFailureCount": 32,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 31,
"decisionTotal": 32,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 16,
"framework_architecture_unsupported": 17,
"model_load": 4,
"repository_structure": 2,
"runtime_memory": 9,
"参数/模板问题": 11
},
"failureCount": 59,
"failureCount": 60,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"pendingCount": 0,
@@ -5369,7 +5369,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 59,
"total": 60,
"unresolvedFailureCount": 28
},
"hygon_k100-ai|vllm|text-generation": {
@@ -5599,26 +5599,26 @@
"unresolvedFailureCount": 63
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 31,
"attributableFailureCount": 32,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 31,
"decisionTotal": 32,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 16,
"framework_architecture_unsupported": 17,
"model_load": 4,
"repository_structure": 2,
"runtime_memory": 9,
"参数/模板问题": 11
},
"failureCount": 59,
"failureCount": 60,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 59,
"total": 60,
"unresolvedFailureCount": 28
},
"vllm_0_17_0_corex_4_4_0": {
@@ -5698,7 +5698,7 @@
"unresolvedFailureCount": 120
}
},
"generatedAt": "2026-09-21T23:30:30.157817+00:00",
"generatedAt": "2026-09-21T23:35:10.920230+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 99,
@@ -6083,16 +6083,16 @@
"unresolvedFailureCount": 1311
},
"hygon_k100-ai": {
"attributableFailureCount": 704,
"decisionFailureRate": 0.9565,
"decisionSuccessRate": 0.0435,
"decisionTotal": 736,
"attributableFailureCount": 705,
"decisionFailureRate": 0.9566,
"decisionSuccessRate": 0.0434,
"decisionTotal": 737,
"failureBreakdown": {
"ambiguous_runtime": 309,
"architecture_compatibility": 32,
"attention_backend": 1,
"context_length": 46,
"framework_architecture_unsupported": 246,
"framework_architecture_unsupported": 247,
"memory_capacity": 58,
"model_load": 62,
"platform_infrastructure": 4,
@@ -6103,14 +6103,14 @@
"日志缺失": 66,
"验证失败": 27
},
"failureCount": 1501,
"failureCount": 1502,
"failureRate": 0.9791,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 32,
"successRate": 0.0209,
"total": 1533,
"total": 1534,
"unresolvedFailureCount": 793
}
},
@@ -17466,6 +17466,29 @@
"total": 2,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_vl|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"modelType": "qwen3_vl",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -38239,6 +38262,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_vl|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_vl",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3|compressed-tensors|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -38527,20 +38574,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16437,
"totalRecords": 16631,
"terminalRecords": 16438,
"totalRecords": 16632,
"totals": {
"attributableFailureCount": 5923,
"attributableFailureCount": 5924,
"decisionFailureRate": 0.8619,
"decisionSuccessRate": 0.1381,
"decisionTotal": 6872,
"decisionTotal": 6873,
"failureBreakdown": {
"ambiguous_runtime": 4052,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 105,
"context_length": 321,
"framework_architecture_unsupported": 2094,
"framework_architecture_unsupported": 2095,
"memory_capacity": 1199,
"model_load": 500,
"platform_infrastructure": 925,
@@ -38551,31 +38598,31 @@
"日志缺失": 719,
"验证失败": 674
},
"failureCount": 15488,
"failureCount": 15489,
"failureRate": 0.9423,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 925,
"successCount": 949,
"successRate": 0.0577,
"total": 16437,
"total": 16438,
"unresolvedFailureCount": 8640
},
"warnings": [
"GPU Iluvatar_mrv-100 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。",
"GPU Kunlunxin_p-800 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-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 Ascend_910-b3 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 Cambricon_mlu-370-x4 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 Cambricon_mlu-370-x8 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 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。",
"组合 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Sunrise_pt-200-x1|vllm_fix_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 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -38615,6 +38662,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16631,
"summarizedRecords": 16632,
"version": 1
}

1000
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

2152
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff