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

state: generation 11831 (cycle_no_slots)

Browse Source
This commit is contained in:
CoolBoy
2026-09-21 22:22:33 +00:00
parent c35c19cb5b
commit caff277cca
7 changed files with 1849 additions and 1781 deletions
Download Patch File Download Diff File Expand all files Collapse all files

247
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T22:17:12.089739+00:00",
"lastSyncTime": "2026-09-21T22:17:11.849675+00:00",
"generatedAt": "2026-09-21T22:22:17.821193+00:00",
"lastSyncTime": "2026-09-21T22:22:17.565358+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3285,9 +3285,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 45
"ambiguous_runtime": 48
},
"failureCount": 45,
"failureCount": 48,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -3297,8 +3297,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 45,
"unresolvedFailureCount": 45
"total": 48,
"unresolvedFailureCount": 48
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 44,
@@ -5630,7 +5630,7 @@
"decisionSuccessRate": 0.0391,
"decisionTotal": 128,
"failureBreakdown": {
"ambiguous_runtime": 204,
"ambiguous_runtime": 207,
"backend_operator": 8,
"framework_architecture_unsupported": 23,
"memory_capacity": 7,
@@ -5639,15 +5639,15 @@
"tokenizer_compatibility": 82,
"参数/模板问题": 13
},
"failureCount": 357,
"failureRate": 0.9862,
"failureCount": 360,
"failureRate": 0.9863,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 17,
"successCount": 5,
"successRate": 0.0138,
"total": 362,
"unresolvedFailureCount": 217
"successRate": 0.0137,
"total": 365,
"unresolvedFailureCount": 220
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 78,
@@ -5677,7 +5677,7 @@
"unresolvedFailureCount": 120
}
},
"generatedAt": "2026-09-21T22:17:12.079068+00:00",
"generatedAt": "2026-09-21T22:22:17.810626+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 99,
@@ -5739,7 +5739,7 @@
"decisionSuccessRate": 0.1185,
"decisionTotal": 211,
"failureBreakdown": {
"ambiguous_runtime": 186,
"ambiguous_runtime": 189,
"backend_operator": 4,
"context_length": 10,
"framework_architecture_unsupported": 120,
@@ -5753,15 +5753,15 @@
"日志缺失": 62,
"验证失败": 27
},
"failureCount": 677,
"failureRate": 0.9644,
"failureCount": 680,
"failureRate": 0.9645,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 25,
"successRate": 0.0356,
"total": 702,
"unresolvedFailureCount": 489
"successRate": 0.0355,
"total": 705,
"unresolvedFailureCount": 492
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 717,
@@ -8186,9 +8186,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "llama",
@@ -8200,8 +8200,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Biren_166m|vllm_fix_tokenizer|text-generation|llama|none": {
"attributableFailureCount": 0,
@@ -8249,6 +8249,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|mpt|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": "mpt",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|qwen2|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -8278,9 +8301,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5_moe",
@@ -8292,8 +8315,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 0,
@@ -17823,7 +17846,7 @@
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T22:08:11.958925+00:00",
"lastTerminalAt": "2026-09-21T22:22:17.565334+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -18046,21 +18069,21 @@
"unresolvedFailureCount": 6
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 5,
"backend_operator": 1,
"framework_architecture_unsupported": 3,
"framework_architecture_unsupported": 1,
"memory_capacity": 1,
"model_load": 1,
"参数/模板问题": 1
},
"failureCount": 12,
"failureCount": 10,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"lastPlatformFailureAt": null,
@@ -18072,7 +18095,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 12,
"total": 10,
"unresolvedFailureCount": 6
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation": {
@@ -18671,12 +18694,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-21T19:05:56.949067+00:00",
"lastTerminalAt": "2026-09-21T22:22:17.565334+00:00",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -18686,8 +18709,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Biren_166m|vllm_fix_tokenizer|text-generation|llama|none": {
"attributableFailureCount": 0,
@@ -18739,6 +18762,31 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|mpt|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": "2026-09-21T22:22:17.565349+00:00",
"modelType": "mpt",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|qwen2|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -18771,9 +18819,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-21T16:50:30.559167+00:00",
@@ -18786,8 +18834,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 0,
@@ -20594,31 +20642,6 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|gemma4|none": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"lastTerminalAt": "2026-09-20T12:21:49.901731+00:00",
"modelType": "gemma4",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|lfm2|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -21072,15 +21095,15 @@
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5|none": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 1,
"failureBreakdown": {
"memory_capacity": 2
"memory_capacity": 1
},
"failureCount": 2,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-20T12:21:49.901832+00:00",
@@ -21093,7 +21116,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 2,
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|spark2_5|fp8": {
@@ -24826,6 +24849,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|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": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|llama|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -24874,6 +24921,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|mpt|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": "mpt",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|qwen2|none|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -24904,9 +24975,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 34,
@@ -24919,8 +24990,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|34": {
"attributableFailureCount": 0,
@@ -38392,15 +38463,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16425,
"totalRecords": 16619,
"terminalRecords": 16428,
"totalRecords": 16622,
"totals": {
"attributableFailureCount": 5921,
"decisionFailureRate": 0.8619,
"decisionSuccessRate": 0.1381,
"decisionTotal": 6870,
"failureBreakdown": {
"ambiguous_runtime": 4045,
"ambiguous_runtime": 4048,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 105,
@@ -38416,31 +38487,31 @@
"日志缺失": 719,
"验证失败": 674
},
"failureCount": 15476,
"failureCount": 15479,
"failureRate": 0.9422,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 925,
"successCount": 949,
"successRate": 0.0578,
"total": 16425,
"unresolvedFailureCount": 8630
"total": 16428,
"unresolvedFailureCount": 8633
},
"warnings": [
"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。",
"GPU Cambricon_mlu-370-x8 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 MetaX_c-500 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。",
"GPU Sunrise_pt-200-x1 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 Vastai_va16 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-150 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 hygon_k100-ai 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。",
"组合 Iluvatar_bi-150|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 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 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。",
@@ -38480,6 +38551,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16619,
"summarizedRecords": 16622,
"version": 1
}