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

state: generation 13295 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-23 02:31:54 +00:00
parent eb5c6ac580
commit 91aa007ccf
9 changed files with 1753 additions and 1682 deletions
Download Patch File Download Diff File Expand all files Collapse all files

142
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-23T02:15:14.481703+00:00",
"lastSyncTime": "2026-09-23T02:15:13.670755+00:00",
"generatedAt": "2026-09-23T02:31:29.894121+00:00",
"lastSyncTime": "2026-09-23T02:31:28.170137+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3481,10 +3481,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 105,
"ambiguous_runtime": 106,
"memory_capacity": 1
},
"failureCount": 106,
"failureCount": 107,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -3494,8 +3494,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 106,
"unresolvedFailureCount": 105
"total": 107,
"unresolvedFailureCount": 106
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 44,
@@ -5840,7 +5840,7 @@
"decisionSuccessRate": 0.0357,
"decisionTotal": 140,
"failureBreakdown": {
"ambiguous_runtime": 298,
"ambiguous_runtime": 299,
"backend_operator": 9,
"framework_architecture_unsupported": 29,
"memory_capacity": 10,
@@ -5849,15 +5849,15 @@
"tokenizer_compatibility": 82,
"参数/模板问题": 13
},
"failureCount": 465,
"failureCount": 466,
"failureRate": 0.9894,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 19,
"successCount": 5,
"successRate": 0.0106,
"total": 470,
"unresolvedFailureCount": 311
"total": 471,
"unresolvedFailureCount": 312
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 107,
@@ -5888,7 +5888,7 @@
"unresolvedFailureCount": 175
}
},
"generatedAt": "2026-09-23T02:15:14.468487+00:00",
"generatedAt": "2026-09-23T02:31:29.882498+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 102,
@@ -5950,7 +5950,7 @@
"decisionSuccessRate": 0.1179,
"decisionTotal": 212,
"failureBreakdown": {
"ambiguous_runtime": 248,
"ambiguous_runtime": 249,
"backend_operator": 4,
"context_length": 10,
"framework_architecture_unsupported": 120,
@@ -5964,15 +5964,15 @@
"日志缺失": 62,
"验证失败": 27
},
"failureCount": 740,
"failureRate": 0.9673,
"failureCount": 741,
"failureRate": 0.9674,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 25,
"successRate": 0.0327,
"total": 765,
"unresolvedFailureCount": 551
"successRate": 0.0326,
"total": 766,
"unresolvedFailureCount": 552
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 723,
@@ -9339,6 +9339,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|spark2_5|fp8": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "fp8",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|spark2_5|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -20865,9 +20888,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 17
"ambiguous_runtime": 16
},
"failureCount": 17,
"failureCount": 16,
"failureRate": 1.0,
"framework": "transformers",
"lastPlatformFailureAt": null,
@@ -20879,8 +20902,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 17,
"unresolvedFailureCount": 17
"total": 16,
"unresolvedFailureCount": 16
},
"Iluvatar_bi-150|transformers|text-generation": {
"attributableFailureCount": 5,
@@ -22300,6 +22323,31 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|spark2_5|fp8": {
"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": "2026-09-23T02:31:28.170137+00:00",
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "fp8",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|spark2_5|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -23032,9 +23080,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 4
"ambiguous_runtime": 3
},
"failureCount": 4,
"failureCount": 3,
"failureRate": 1.0,
"framework": "transformers",
"lastTerminalAt": "2026-09-21T05:42:03.443575+00:00",
@@ -23047,8 +23095,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 4
"total": 3,
"unresolvedFailureCount": 3
},
"Iluvatar_bi-100|transformers|text-generation|qwen3_vl|none": {
"attributableFailureCount": 0,
@@ -29136,6 +29184,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|spark2_5|fp8|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 32,
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "fp8",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|spark2_5|none|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -45730,15 +45802,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16794,
"totalRecords": 17012,
"terminalRecords": 16795,
"totalRecords": 17013,
"totals": {
"attributableFailureCount": 6012,
"decisionFailureRate": 0.8622,
"decisionSuccessRate": 0.1378,
"decisionTotal": 6973,
"failureBreakdown": {
"ambiguous_runtime": 4282,
"ambiguous_runtime": 4283,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 114,
@@ -45754,15 +45826,15 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 15833,
"failureCount": 15834,
"failureRate": 0.9428,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 931,
"successCount": 961,
"successRate": 0.0572,
"total": 16794,
"unresolvedFailureCount": 8890
"total": 16795,
"unresolvedFailureCount": 8891
},
"warnings": [
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -45775,8 +45847,8 @@
"GPU hygon_k100-ai 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 Vastai_va16 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 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。",
@@ -45801,6 +45873,7 @@
"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。",
@@ -45814,11 +45887,10 @@
"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 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 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。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17012,
"summarizedRecords": 17013,
"version": 1
}