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

state: generation 16850 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-26 22:23:55 +00:00
parent a8a497d402
commit 8bb50505f6
10 changed files with 1583 additions and 1514 deletions
Download Patch File Download Diff File Expand all files Collapse all files

160
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-26T21:44:29.041738+00:00",
"lastSyncTime": "2026-09-26T21:44:28.758538+00:00",
"generatedAt": "2026-09-26T22:23:09.017195+00:00",
"lastSyncTime": "2026-09-26T22:23:08.761596+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -4925,10 +4925,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 140,
"ambiguous_runtime": 141,
"参数/模板问题": 3
},
"failureCount": 143,
"failureCount": 144,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -4938,8 +4938,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 143,
"unresolvedFailureCount": 143
"total": 144,
"unresolvedFailureCount": 144
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 61,
@@ -6086,7 +6086,7 @@
"decisionSuccessRate": 0.0323,
"decisionTotal": 155,
"failureBreakdown": {
"ambiguous_runtime": 319,
"ambiguous_runtime": 320,
"backend_operator": 9,
"framework_architecture_unsupported": 32,
"memory_capacity": 10,
@@ -6095,15 +6095,15 @@
"tokenizer_compatibility": 90,
"参数/模板问题": 13
},
"failureCount": 502,
"failureRate": 0.9901,
"failureCount": 503,
"failureRate": 0.9902,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 20,
"successCount": 5,
"successRate": 0.0099,
"total": 507,
"unresolvedFailureCount": 332
"successRate": 0.0098,
"total": 508,
"unresolvedFailureCount": 333
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 128,
@@ -6134,7 +6134,7 @@
"unresolvedFailureCount": 196
}
},
"generatedAt": "2026-09-26T21:44:29.028719+00:00",
"generatedAt": "2026-09-26T22:23:09.005096+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 102,
@@ -6365,7 +6365,7 @@
"decisionSuccessRate": 0.066,
"decisionTotal": 106,
"failureBreakdown": {
"ambiguous_runtime": 228,
"ambiguous_runtime": 229,
"backend_operator": 23,
"framework_architecture_unsupported": 37,
"memory_capacity": 3,
@@ -6378,15 +6378,15 @@
"日志缺失": 1,
"验证失败": 23
},
"failureCount": 398,
"failureRate": 0.9827,
"failureCount": 399,
"failureRate": 0.9828,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 7,
"successRate": 0.0173,
"total": 405,
"unresolvedFailureCount": 298
"successRate": 0.0172,
"total": 406,
"unresolvedFailureCount": 299
},
"Kunlunxin_r-200-8f": {
"attributableFailureCount": 0,
@@ -16980,6 +16980,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gpt_oss|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": "gpt_oss",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|hrm_text|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -22798,10 +22821,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 8,
"ambiguous_runtime": 7,
"framework_architecture_unsupported": 1
},
"failureCount": 9,
"failureCount": 8,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -22813,8 +22836,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 9,
"unresolvedFailureCount": 8
"total": 8,
"unresolvedFailureCount": 7
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -23084,13 +23107,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 8
"ambiguous_runtime": 9
},
"failureCount": 8,
"failureCount": 9,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-23T23:59:25.752461+00:00",
"lastTerminalAt": "2026-09-26T22:23:08.761596+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -23098,8 +23121,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 8,
"unresolvedFailureCount": 8
"total": 9,
"unresolvedFailureCount": 9
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 16,
@@ -23899,9 +23922,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 1
},
"failureCount": 2,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-24T05:11:42.061432+00:00",
@@ -23914,8 +23937,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|gemma2|compressed-tensors": {
"attributableFailureCount": 0,
@@ -25192,6 +25215,31 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gpt_oss|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": "2026-09-26T22:23:08.761596+00:00",
"modelType": "gpt_oss",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"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": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -42074,6 +42122,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gpt_oss|none|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 33,
"modelType": "gpt_oss",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|hrm_text|none|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -50980,15 +51052,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17051,
"totalRecords": 17272,
"terminalRecords": 17052,
"totalRecords": 17273,
"totals": {
"attributableFailureCount": 6114,
"decisionFailureRate": 0.8636,
"decisionSuccessRate": 0.1364,
"decisionTotal": 7080,
"failureBreakdown": {
"ambiguous_runtime": 4411,
"ambiguous_runtime": 4412,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
@@ -51004,30 +51076,30 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16085,
"failureCount": 16086,
"failureRate": 0.9433,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 937,
"successCount": 966,
"successRate": 0.0567,
"total": 17051,
"unresolvedFailureCount": 9034
"total": 17052,
"unresolvedFailureCount": 9035
},
"warnings": [
"GPU Biren_166m 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 Iluvatar_bi-100 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 MetaX_c-500 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 Kunlunxin_p-800 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 Cambricon_mlu-370-x8 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 hygon_k100-ai 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 MetaX_c-500 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_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_bi-150|llamacpp|text-generation 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|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -51040,7 +51112,6 @@
"组合 Iluvatar_bi-100|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。",
"组合 Cambricon_mlu-370-x4|vllm-mlu|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。",
"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_tokenizer_patch|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-customized|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -51066,10 +51137,11 @@
"组合 Cambricon_mlu-370-x4|unknown|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 Ascend_910-b4|llamacpp|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 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。",
"组合 MetaX_c-500|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17272,
"summarizedRecords": 17273,
"version": 1
}