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

state: generation 13268 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-23 01:54:42 +00:00
parent 7a2d2525a9
commit 6c5f7d9c01
9 changed files with 1682 additions and 1611 deletions
Download Patch File Download Diff File Expand all files Collapse all files

170
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-23T01:50:33.450442+00:00",
"lastSyncTime": "2026-09-23T01:50:30.356465+00:00",
"generatedAt": "2026-09-23T01:54:28.046097+00:00",
"lastSyncTime": "2026-09-23T01:54:25.558841+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -4698,32 +4698,32 @@
"unresolvedFailureCount": 131
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 39,
"decisionFailureRate": 0.8864,
"decisionSuccessRate": 0.1136,
"decisionTotal": 44,
"attributableFailureCount": 40,
"decisionFailureRate": 0.8889,
"decisionSuccessRate": 0.1111,
"decisionTotal": 45,
"failureBreakdown": {
"ambiguous_runtime": 5,
"backend_operator": 8,
"framework_architecture_unsupported": 15,
"memory_capacity": 1,
"model_load": 11,
"model_load": 12,
"platform_infrastructure": 1,
"repository_structure": 2,
"runtime_memory": 2,
"参数/模板问题": 14
},
"failureCount": 59,
"failureRate": 0.9219,
"failureCount": 60,
"failureRate": 0.9231,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 5,
"successRate": 0.0781,
"successRate": 0.0769,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 64,
"total": 65,
"unresolvedFailureCount": 19
},
"Kunlunxin_p-800|vllm|text-generation": {
@@ -5858,35 +5858,35 @@
"unresolvedFailureCount": 310
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 106,
"decisionFailureRate": 0.9298,
"decisionSuccessRate": 0.0702,
"decisionTotal": 114,
"attributableFailureCount": 107,
"decisionFailureRate": 0.9304,
"decisionSuccessRate": 0.0696,
"decisionTotal": 115,
"failureBreakdown": {
"ambiguous_runtime": 145,
"backend_operator": 8,
"context_length": 4,
"framework_architecture_unsupported": 71,
"memory_capacity": 2,
"model_load": 14,
"model_load": 15,
"platform_infrastructure": 2,
"repository_structure": 3,
"runtime_memory": 2,
"tokenizer_compatibility": 2,
"参数/模板问题": 28
},
"failureCount": 281,
"failureRate": 0.9723,
"failureCount": 282,
"failureRate": 0.9724,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 8,
"successRate": 0.0277,
"total": 289,
"successRate": 0.0276,
"total": 290,
"unresolvedFailureCount": 173
}
},
"generatedAt": "2026-09-23T01:50:33.438949+00:00",
"generatedAt": "2026-09-23T01:54:28.035119+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 102,
@@ -6112,16 +6112,16 @@
"unresolvedFailureCount": 717
},
"Kunlunxin_p-800": {
"attributableFailureCount": 51,
"decisionFailureRate": 0.9107,
"decisionSuccessRate": 0.0893,
"decisionTotal": 56,
"attributableFailureCount": 52,
"decisionFailureRate": 0.9123,
"decisionSuccessRate": 0.0877,
"decisionTotal": 57,
"failureBreakdown": {
"ambiguous_runtime": 209,
"backend_operator": 10,
"framework_architecture_unsupported": 23,
"memory_capacity": 2,
"model_load": 12,
"model_load": 13,
"platform_infrastructure": 1,
"repository_structure": 2,
"runtime_memory": 2,
@@ -6129,14 +6129,14 @@
"日志缺失": 1,
"验证失败": 23
},
"failureCount": 317,
"failureCount": 318,
"failureRate": 0.9845,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 5,
"successRate": 0.0155,
"total": 322,
"total": 323,
"unresolvedFailureCount": 265
},
"Kunlunxin_r-200-8f": {
@@ -16914,6 +16914,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|hrm_text|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "hrm_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|lfm2|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -21044,17 +21067,17 @@
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"model_load": 1,
"model_load": 2,
"参数/模板问题": 1
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastPlatformFailureAt": null,
@@ -21066,7 +21089,7 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm|text-generation": {
@@ -22209,9 +22232,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 8
"ambiguous_runtime": 7
},
"failureCount": 8,
"failureCount": 7,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-22T16:15:27.384896+00:00",
@@ -22224,8 +22247,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 8,
"unresolvedFailureCount": 8
"total": 7,
"unresolvedFailureCount": 7
},
"Biren_166m|vllm_fix_tokenizer|text-generation|qwen3|compressed-tensors": {
"attributableFailureCount": 0,
@@ -23953,6 +23976,31 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|hrm_text|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-23T01:54:25.558841+00:00",
"modelType": "hrm_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|lfm2|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -40198,6 +40246,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|hrm_text|none|31": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 31,
"modelType": "hrm_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|lfm2|none|29": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -45634,13 +45706,13 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16787,
"totalRecords": 17005,
"terminalRecords": 16788,
"totalRecords": 17006,
"totals": {
"attributableFailureCount": 6009,
"attributableFailureCount": 6010,
"decisionFailureRate": 0.8621,
"decisionSuccessRate": 0.1379,
"decisionTotal": 6970,
"decisionTotal": 6971,
"failureBreakdown": {
"ambiguous_runtime": 4279,
"architecture_compatibility": 212,
@@ -45649,7 +45721,7 @@
"context_length": 322,
"framework_architecture_unsupported": 2131,
"memory_capacity": 1203,
"model_load": 525,
"model_load": 526,
"platform_infrastructure": 930,
"repository_structure": 740,
"runtime_memory": 91,
@@ -45658,19 +45730,20 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 15826,
"failureCount": 15827,
"failureRate": 0.9428,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 930,
"successCount": 961,
"successRate": 0.0572,
"total": 16787,
"total": 16788,
"unresolvedFailureCount": 8887
},
"warnings": [
"GPU Iluvatar_mrv-100 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 Biren_166m 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-x8 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。",
@@ -45681,7 +45754,6 @@
"GPU Vastai_va16 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 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。",
"组合 Iluvatar_bi-150|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 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。",
@@ -45705,7 +45777,6 @@
"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 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。",
"组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|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 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 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 Sunrise_pt-200-x1|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -45719,10 +45790,11 @@
"组合 Mthreads_s4000|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|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 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 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-b3|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": 17005,
"summarizedRecords": 17006,
"version": 1
}