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

state: generation 4888 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 01:44:14 +00:00
parent 0e12ba6ba9
commit 0ae011cf21
10 changed files with 1940 additions and 1918 deletions
Download Patch File Download Diff File Expand all files Collapse all files

130
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T01:16:26.316475+00:00",
"lastSyncTime": "2026-09-10T01:16:26.008867+00:00",
"generatedAt": "2026-09-10T01:42:35.052275+00:00",
"lastSyncTime": "2026-09-10T01:42:34.770281+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1565,25 +1565,25 @@
"decisionSuccessRate": 0.2222,
"decisionTotal": 9,
"failureBreakdown": {
"ambiguous_runtime": 10,
"ambiguous_runtime": 11,
"framework_architecture_unsupported": 5,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 5,
"验证失败": 22
},
"failureCount": 44,
"failureRate": 0.9565,
"failureCount": 45,
"failureRate": 0.9574,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0435,
"successRate": 0.0426,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 46,
"unresolvedFailureCount": 37
"total": 47,
"unresolvedFailureCount": 38
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 7,
@@ -1861,10 +1861,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 20,
"ambiguous_runtime": 21,
"参数/模板问题": 1
},
"failureCount": 21,
"failureCount": 22,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -1874,8 +1874,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 21,
"unresolvedFailureCount": 21
"total": 22,
"unresolvedFailureCount": 22
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2289,7 +2289,7 @@
"decisionSuccessRate": 0.2883,
"decisionTotal": 163,
"failureBreakdown": {
"ambiguous_runtime": 93,
"ambiguous_runtime": 94,
"backend_operator": 2,
"framework_architecture_unsupported": 83,
"memory_capacity": 5,
@@ -2298,15 +2298,15 @@
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 938,
"failureCount": 939,
"failureRate": 0.9523,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 47,
"successRate": 0.0477,
"total": 985,
"unresolvedFailureCount": 822
"total": 986,
"unresolvedFailureCount": 823
},
"vllm": {
"attributableFailureCount": 227,
@@ -2400,22 +2400,22 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 32,
"failureBreakdown": {
"ambiguous_runtime": 21,
"ambiguous_runtime": 22,
"framework_architecture_unsupported": 4,
"model_load": 1,
"platform_infrastructure": 1,
"tokenizer_compatibility": 27,
"参数/模板问题": 7
},
"failureCount": 61,
"failureCount": 62,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"total": 61,
"unresolvedFailureCount": 28
"total": 62,
"unresolvedFailureCount": 29
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 0,
@@ -2436,7 +2436,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T01:16:26.312138+00:00",
"generatedAt": "2026-09-10T01:42:35.047837+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2538,22 +2538,22 @@
"decisionSuccessRate": 0.1053,
"decisionTotal": 19,
"failureBreakdown": {
"ambiguous_runtime": 23,
"ambiguous_runtime": 24,
"framework_architecture_unsupported": 15,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 17,
"验证失败": 22
},
"failureCount": 79,
"failureRate": 0.9753,
"failureCount": 80,
"failureRate": 0.9756,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0247,
"total": 81,
"unresolvedFailureCount": 62
"successRate": 0.0244,
"total": 82,
"unresolvedFailureCount": 63
},
"Iluvatar_bi-100": {
"attributableFailureCount": 0,
@@ -2627,20 +2627,20 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 51,
"ambiguous_runtime": 52,
"memory_capacity": 1,
"参数/模板问题": 1,
"验证失败": 23
},
"failureCount": 76,
"failureCount": 77,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 76,
"unresolvedFailureCount": 75
"total": 77,
"unresolvedFailureCount": 76
},
"MetaX_c-500": {
"attributableFailureCount": 38,
@@ -3245,9 +3245,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
"ambiguous_runtime": 4
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "llama",
@@ -3259,8 +3259,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 4,
"unresolvedFailureCount": 4
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|phi3small|compressed-tensors": {
"attributableFailureCount": 0,
@@ -4071,24 +4071,24 @@
"decisionSuccessRate": 0.3333,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 6,
"ambiguous_runtime": 7,
"framework_architecture_unsupported": 3,
"tokenizer_compatibility": 1
},
"failureCount": 10,
"failureRate": 0.8333,
"failureCount": 11,
"failureRate": 0.8462,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-09T23:14:19.142084+00:00",
"lastTerminalAt": "2026-09-10T01:42:34.770281+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.1667,
"successRate": 0.1538,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 12,
"unresolvedFailureCount": 6
"total": 13,
"unresolvedFailureCount": 7
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 4,
@@ -5804,6 +5804,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|28": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 28,
"modelType": "llama",
"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|llama|compressed-tensors|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -6741,15 +6765,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1474,
"totalRecords": 1558,
"terminalRecords": 1476,
"totalRecords": 1560,
"totals": {
"attributableFailureCount": 390,
"decisionFailureRate": 0.8904,
"decisionSuccessRate": 0.1096,
"decisionTotal": 438,
"failureBreakdown": {
"ambiguous_runtime": 267,
"ambiguous_runtime": 269,
"backend_operator": 25,
"framework_architecture_unsupported": 266,
"memory_capacity": 11,
@@ -6761,21 +6785,21 @@
"参数/模板问题": 94,
"验证失败": 673
},
"failureCount": 1426,
"failureRate": 0.9674,
"failureCount": 1428,
"failureRate": 0.9675,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 48,
"successRate": 0.0326,
"total": 1474,
"unresolvedFailureCount": 1034
"successRate": 0.0325,
"total": 1476,
"unresolvedFailureCount": 1036
},
"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。",
@@ -6783,7 +6807,7 @@
"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。",
@@ -6804,6 +6828,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1558,
"summarizedRecords": 1560,
"version": 1
}