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

state: generation 21840 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-07 13:31:17 +00:00
parent f21a201a19
commit 39ccdbf1c9
9 changed files with 1941 additions and 1870 deletions
Download Patch File Download Diff File Expand all files Collapse all files

138
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-07T13:20:53.520866+00:00",
"lastSyncTime": "2026-10-07T13:20:53.257507+00:00",
"generatedAt": "2026-10-07T13:29:12.029835+00:00",
"lastSyncTime": "2026-10-07T13:29:11.757335+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -4083,10 +4083,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 9,
"failureBreakdown": {
"ambiguous_runtime": 48,
"ambiguous_runtime": 49,
"memory_capacity": 9
},
"failureCount": 57,
"failureCount": 58,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -4096,8 +4096,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 57,
"unresolvedFailureCount": 48
"total": 58,
"unresolvedFailureCount": 49
},
"Iluvatar_bi-150|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 10,
@@ -5632,7 +5632,7 @@
"decisionSuccessRate": 0.0281,
"decisionTotal": 178,
"failureBreakdown": {
"ambiguous_runtime": 367,
"ambiguous_runtime": 368,
"backend_operator": 9,
"framework_architecture_unsupported": 47,
"memory_capacity": 10,
@@ -5641,15 +5641,15 @@
"tokenizer_compatibility": 95,
"参数/模板问题": 13
},
"failureCount": 578,
"failureCount": 579,
"failureRate": 0.9914,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 25,
"successCount": 5,
"successRate": 0.0086,
"total": 583,
"unresolvedFailureCount": 380
"total": 584,
"unresolvedFailureCount": 381
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 155,
@@ -5680,7 +5680,7 @@
"unresolvedFailureCount": 237
}
},
"generatedAt": "2026-10-07T13:20:53.504133+00:00",
"generatedAt": "2026-10-07T13:29:12.012347+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 119,
@@ -5850,7 +5850,7 @@
"decisionSuccessRate": 0.1639,
"decisionTotal": 915,
"failureBreakdown": {
"ambiguous_runtime": 661,
"ambiguous_runtime": 662,
"architecture_compatibility": 15,
"backend_operator": 12,
"context_length": 29,
@@ -5865,15 +5865,15 @@
"日志缺失": 155,
"验证失败": 30
},
"failureCount": 1953,
"failureCount": 1954,
"failureRate": 0.9287,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 21,
"successCount": 150,
"successRate": 0.0713,
"total": 2103,
"unresolvedFailureCount": 1167
"total": 2104,
"unresolvedFailureCount": 1168
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 984,
@@ -16458,6 +16458,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|mini_k3|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "mini_k3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|nemotron_h|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -25553,14 +25576,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 15,
"ambiguous_runtime": 16,
"memory_capacity": 2
},
"failureCount": 17,
"failureCount": 18,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-10-07T09:53:21.160613+00:00",
"lastTerminalAt": "2026-10-07T13:29:11.757302+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -25568,8 +25591,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 17,
"unresolvedFailureCount": 15
"total": 18,
"unresolvedFailureCount": 16
},
"Iluvatar_bi-150|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 7,
@@ -27202,9 +27225,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 4
"ambiguous_runtime": 3
},
"failureCount": 4,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm-customized",
"lastTerminalAt": "2026-09-22T18:31:46.771079+00:00",
@@ -27217,8 +27240,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 4
"total": 3,
"unresolvedFailureCount": 3
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|mistral|compressed-tensors": {
"attributableFailureCount": 0,
@@ -27645,6 +27668,31 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|mini_k3|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-10-07T13:29:11.757302+00:00",
"modelType": "mini_k3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|phi3small|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -45254,6 +45302,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|mini_k3|none|30": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 30,
"modelType": "mini_k3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|nemotron_h|compressed-tensors|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -58286,15 +58358,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17381,
"totalRecords": 17638,
"terminalRecords": 17382,
"totalRecords": 17639,
"totals": {
"attributableFailureCount": 6247,
"decisionFailureRate": 0.8646,
"decisionSuccessRate": 0.1354,
"decisionTotal": 7225,
"failureBreakdown": {
"ambiguous_runtime": 4563,
"ambiguous_runtime": 4564,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 129,
@@ -58310,15 +58382,15 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16403,
"failureCount": 16404,
"failureRate": 0.9437,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 952,
"successCount": 978,
"successRate": 0.0563,
"total": 17381,
"unresolvedFailureCount": 9204
"total": 17382,
"unresolvedFailureCount": 9205
},
"warnings": [
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -58327,14 +58399,14 @@
"GPU hygon_k100-ai 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 Ascend_910-b3 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_mrv-100 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 Cambricon_mlu-370-x8 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-b4 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-100 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 Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
"组合 Vastai_va16|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-b3|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 Iluvatar_mrv-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -58379,6 +58451,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17638,
"summarizedRecords": 17639,
"version": 1
}