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

state: generation 6185 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-12 12:01:00 +00:00
parent 5c4ad9e1fd
commit 3fcf64f78c
9 changed files with 1910 additions and 1863 deletions
Download Patch File Download Diff File Expand all files Collapse all files

112
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-12T11:41:06.223671+00:00",
"lastSyncTime": "2026-09-12T11:41:06.016003+00:00",
"generatedAt": "2026-09-12T11:59:10.224777+00:00",
"lastSyncTime": "2026-09-12T11:59:10.019448+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1591,14 +1591,15 @@
"unresolvedFailureCount": 53
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 1,
"model_load": 1
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1608,7 +1609,7 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -2416,14 +2417,14 @@
"unresolvedFailureCount": 865
},
"vllm": {
"attributableFailureCount": 269,
"attributableFailureCount": 270,
"decisionFailureRate": 0.989,
"decisionSuccessRate": 0.011,
"decisionTotal": 272,
"decisionTotal": 273,
"failureBreakdown": {
"ambiguous_runtime": 200,
"backend_operator": 34,
"framework_architecture_unsupported": 184,
"framework_architecture_unsupported": 185,
"memory_capacity": 6,
"model_load": 25,
"platform_infrastructure": 1,
@@ -2432,14 +2433,14 @@
"tokenizer_compatibility": 6,
"参数/模板问题": 24
},
"failureCount": 494,
"failureCount": 495,
"failureRate": 0.994,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.006,
"total": 497,
"total": 498,
"unresolvedFailureCount": 224
},
"vllm-mlu": {
@@ -2544,7 +2545,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T11:41:06.218874+00:00",
"generatedAt": "2026-09-12T11:59:10.220753+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2595,27 +2596,27 @@
"unresolvedFailureCount": 223
},
"Biren_166m": {
"attributableFailureCount": 29,
"decisionFailureRate": 0.9667,
"decisionSuccessRate": 0.0333,
"decisionTotal": 30,
"attributableFailureCount": 30,
"decisionFailureRate": 0.9677,
"decisionSuccessRate": 0.0323,
"decisionTotal": 31,
"failureBreakdown": {
"ambiguous_runtime": 26,
"backend_operator": 4,
"framework_architecture_unsupported": 20,
"framework_architecture_unsupported": 21,
"memory_capacity": 1,
"model_load": 3,
"tokenizer_compatibility": 1,
"验证失败": 27
},
"failureCount": 82,
"failureRate": 0.988,
"failureCount": 83,
"failureRate": 0.9881,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.012,
"total": 83,
"successRate": 0.0119,
"total": 84,
"unresolvedFailureCount": 53
},
"Cambricon_mlu-370-x4": {
@@ -2938,6 +2939,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|gemma2|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -5149,6 +5173,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|compressed-tensors|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|gemma2|compressed-tensors|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -7208,17 +7256,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1717,
"totalRecords": 1804,
"terminalRecords": 1718,
"totalRecords": 1805,
"totals": {
"attributableFailureCount": 479,
"decisionFailureRate": 0.8937,
"decisionSuccessRate": 0.1063,
"decisionTotal": 536,
"attributableFailureCount": 480,
"decisionFailureRate": 0.8939,
"decisionSuccessRate": 0.1061,
"decisionTotal": 537,
"failureBreakdown": {
"ambiguous_runtime": 403,
"backend_operator": 42,
"framework_architecture_unsupported": 293,
"framework_architecture_unsupported": 294,
"memory_capacity": 11,
"model_load": 71,
"platform_infrastructure": 4,
@@ -7228,20 +7276,21 @@
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1660,
"failureCount": 1661,
"failureRate": 0.9668,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 57,
"successRate": 0.0332,
"total": 1717,
"total": 1718,
"unresolvedFailureCount": 1177
},
"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。",
@@ -7250,7 +7299,6 @@
"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。",
@@ -7272,6 +7320,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1804,
"summarizedRecords": 1805,
"version": 1
}