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

state: generation 21912 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-07 16:15:35 +00:00
parent 14afd5b2b1
commit 6d910da384
9 changed files with 2130 additions and 2111 deletions
Download Patch File Download Diff File Expand all files Collapse all files

203
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-07T16:06:19.430450+00:00",
"lastSyncTime": "2026-10-07T16:06:19.147209+00:00",
"generatedAt": "2026-10-07T16:13:00.043287+00:00",
"lastSyncTime": "2026-10-07T16:12:59.741980+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3219,10 +3219,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 129,
"ambiguous_runtime": 131,
"memory_capacity": 1
},
"failureCount": 130,
"failureCount": 132,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -3232,8 +3232,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 130,
"unresolvedFailureCount": 129
"total": 132,
"unresolvedFailureCount": 131
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 50,
@@ -5633,7 +5633,7 @@
"decisionSuccessRate": 0.0278,
"decisionTotal": 180,
"failureBreakdown": {
"ambiguous_runtime": 371,
"ambiguous_runtime": 373,
"backend_operator": 9,
"framework_architecture_unsupported": 48,
"memory_capacity": 10,
@@ -5642,15 +5642,15 @@
"tokenizer_compatibility": 95,
"参数/模板问题": 13
},
"failureCount": 584,
"failureCount": 586,
"failureRate": 0.9915,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 25,
"successCount": 5,
"successRate": 0.0085,
"total": 589,
"unresolvedFailureCount": 384
"total": 591,
"unresolvedFailureCount": 386
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 155,
@@ -5681,7 +5681,7 @@
"unresolvedFailureCount": 257
}
},
"generatedAt": "2026-10-07T16:06:19.414363+00:00",
"generatedAt": "2026-10-07T16:12:59.974916+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 119,
@@ -5744,7 +5744,7 @@
"decisionSuccessRate": 0.1147,
"decisionTotal": 218,
"failureBreakdown": {
"ambiguous_runtime": 273,
"ambiguous_runtime": 275,
"backend_operator": 4,
"context_length": 10,
"framework_architecture_unsupported": 125,
@@ -5758,15 +5758,15 @@
"日志缺失": 62,
"验证失败": 27
},
"failureCount": 771,
"failureRate": 0.9686,
"failureCount": 773,
"failureRate": 0.9687,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 25,
"successRate": 0.0314,
"total": 796,
"unresolvedFailureCount": 576
"successRate": 0.0313,
"total": 798,
"unresolvedFailureCount": 578
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 759,
@@ -9157,6 +9157,29 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Biren_166m|vllm_fix_tokenizer|text-generation|mini_k3|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
},
"failureCount": 2,
"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": "Biren_166m",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
},
"Biren_166m|vllm_fix_tokenizer|text-generation|mistral3|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -25342,9 +25365,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 12
"ambiguous_runtime": 14
},
"failureCount": 12,
"failureCount": 14,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
@@ -25356,8 +25379,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 12,
"unresolvedFailureCount": 12
"total": 14,
"unresolvedFailureCount": 14
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -25489,18 +25512,17 @@
"unresolvedFailureCount": 7
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 1,
"参数/模板问题": 1
},
"failureCount": 19,
"failureCount": 18,
"failureRate": 1.0,
"framework": "vllm-customized",
"lastPlatformFailureAt": null,
@@ -25512,7 +25534,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 19,
"total": 18,
"unresolvedFailureCount": 18
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
@@ -25654,10 +25676,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 2,
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 1
},
"failureCount": 3,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -25669,8 +25691,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 2
"total": 2,
"unresolvedFailureCount": 1
},
"Iluvatar_mrv-100|vllm|text-generation": {
"attributableFailureCount": 1,
@@ -26493,6 +26515,31 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|mini_k3|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-10-07T16:12:59.741949+00:00",
"modelType": "mini_k3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
},
"Biren_166m|vllm_fix_tokenizer|text-generation|muse_glimmer|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -26968,31 +27015,6 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|nemotron_h|compressed-tensors": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-customized",
"lastTerminalAt": "2026-09-22T13:37:53.563484+00:00",
"modelType": "nemotron_h",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|phi3|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -27944,31 +27966,6 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm|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",
"lastTerminalAt": "2026-09-21T17:41:26.757140+00:00",
"modelType": "mpt",
"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|text-generation|zaya|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -34370,6 +34367,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|mini_k3|none|30": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
},
"failureCount": 2,
"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": "Biren_166m",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
},
"Biren_166m|vllm_fix_tokenizer|text-generation|mistral3|none|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -58329,15 +58350,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17409,
"totalRecords": 17666,
"terminalRecords": 17411,
"totalRecords": 17668,
"totals": {
"attributableFailureCount": 6249,
"decisionFailureRate": 0.8647,
"decisionSuccessRate": 0.1353,
"decisionTotal": 7227,
"failureBreakdown": {
"ambiguous_runtime": 4569,
"ambiguous_runtime": 4571,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 129,
@@ -58353,15 +58374,15 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16431,
"failureCount": 16433,
"failureRate": 0.9438,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 952,
"successCount": 978,
"successRate": 0.0562,
"total": 17409,
"unresolvedFailureCount": 9230
"total": 17411,
"unresolvedFailureCount": 9232
},
"warnings": [
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -58370,14 +58391,14 @@
"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 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 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 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。",
"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。",
@@ -58422,6 +58443,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17666,
"summarizedRecords": 17668,
"version": 1
}