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

state: generation 5158 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 12:25:24 +00:00
parent e2f33f29de
commit 689778e031
10 changed files with 2081 additions and 2081 deletions
Download Patch File Download Diff File Expand all files Collapse all files

215
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T12:15:14.576026+00:00",
"lastSyncTime": "2026-09-10T12:15:14.346623+00:00",
"generatedAt": "2026-09-10T12:23:25.924304+00:00",
"lastSyncTime": "2026-09-10T12:23:25.501745+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1868,10 +1868,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 29,
"ambiguous_runtime": 30,
"参数/模板问题": 1
},
"failureCount": 30,
"failureCount": 31,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -1881,8 +1881,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 30,
"unresolvedFailureCount": 30
"total": 31,
"unresolvedFailureCount": 31
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2145,12 +2145,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 44,
"failureBreakdown": {
"ambiguous_runtime": 52,
"ambiguous_runtime": 55,
"framework_architecture_unsupported": 38,
"memory_capacity": 1,
"model_load": 5
},
"failureCount": 96,
"failureCount": 99,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2160,8 +2160,8 @@
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 96,
"unresolvedFailureCount": 52
"total": 99,
"unresolvedFailureCount": 55
},
"hygon_k100-ai|llamacpp|text-generation": {
"attributableFailureCount": 0,
@@ -2228,19 +2228,19 @@
"unresolvedFailureCount": 8
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 35,
"attributableFailureCount": 36,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 35,
"decisionTotal": 36,
"failureBreakdown": {
"ambiguous_runtime": 15,
"ambiguous_runtime": 16,
"framework_architecture_unsupported": 27,
"memory_capacity": 1,
"model_load": 3,
"repository_structure": 3,
"runtime_memory": 1
"runtime_memory": 2
},
"failureCount": 50,
"failureCount": 52,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2250,8 +2250,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 50,
"unresolvedFailureCount": 15
"total": 52,
"unresolvedFailureCount": 16
}
},
"frameworkSummaries": {
@@ -2318,31 +2318,31 @@
"unresolvedFailureCount": 844
},
"vllm": {
"attributableFailureCount": 235,
"attributableFailureCount": 236,
"decisionFailureRate": 0.9958,
"decisionSuccessRate": 0.0042,
"decisionTotal": 236,
"decisionTotal": 237,
"failureBreakdown": {
"ambiguous_runtime": 167,
"ambiguous_runtime": 171,
"backend_operator": 29,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
"model_load": 18,
"platform_infrastructure": 1,
"repository_structure": 5,
"runtime_memory": 5,
"runtime_memory": 6,
"tokenizer_compatibility": 3,
"参数/模板问题": 24
},
"failureCount": 427,
"failureCount": 432,
"failureRate": 0.9977,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 1,
"successRate": 0.0023,
"total": 428,
"unresolvedFailureCount": 191
"total": 433,
"unresolvedFailureCount": 195
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2409,22 +2409,22 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 37,
"failureBreakdown": {
"ambiguous_runtime": 30,
"ambiguous_runtime": 31,
"framework_architecture_unsupported": 4,
"model_load": 1,
"platform_infrastructure": 2,
"tokenizer_compatibility": 32,
"参数/模板问题": 7
},
"failureCount": 76,
"failureCount": 77,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 0,
"successRate": 0.0,
"total": 76,
"unresolvedFailureCount": 37
"total": 77,
"unresolvedFailureCount": 38
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 0,
@@ -2445,7 +2445,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T12:15:14.571193+00:00",
"generatedAt": "2026-09-10T12:23:25.917637+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2636,20 +2636,20 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 61,
"ambiguous_runtime": 62,
"memory_capacity": 1,
"参数/模板问题": 1,
"验证失败": 23
},
"failureCount": 86,
"failureCount": 87,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 86,
"unresolvedFailureCount": 85
"total": 87,
"unresolvedFailureCount": 86
},
"MetaX_c-500": {
"attributableFailureCount": 42,
@@ -2730,47 +2730,47 @@
"decisionSuccessRate": 0.2167,
"decisionTotal": 60,
"failureBreakdown": {
"ambiguous_runtime": 53,
"ambiguous_runtime": 56,
"framework_architecture_unsupported": 40,
"memory_capacity": 1,
"model_load": 6,
"参数/模板问题": 13,
"验证失败": 130
},
"failureCount": 243,
"failureRate": 0.9492,
"failureCount": 246,
"failureRate": 0.9498,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.0508,
"total": 256,
"unresolvedFailureCount": 196
"successRate": 0.0502,
"total": 259,
"unresolvedFailureCount": 199
},
"hygon_k100-ai": {
"attributableFailureCount": 38,
"attributableFailureCount": 39,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 38,
"decisionTotal": 39,
"failureBreakdown": {
"ambiguous_runtime": 17,
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 30,
"memory_capacity": 1,
"model_load": 3,
"repository_structure": 3,
"runtime_memory": 1,
"runtime_memory": 2,
"参数/模板问题": 8,
"验证失败": 27
},
"failureCount": 90,
"failureCount": 92,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 90,
"unresolvedFailureCount": 52
"total": 92,
"unresolvedFailureCount": 53
}
},
"observedGpuMemoryGiB": {
@@ -3276,9 +3276,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "gemma2",
@@ -3290,8 +3290,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 0,
@@ -4309,9 +4309,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 14
"ambiguous_runtime": 15
},
"failureCount": 14,
"failureCount": 15,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
@@ -4323,8 +4323,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 14,
"unresolvedFailureCount": 14
"total": 15,
"unresolvedFailureCount": 15
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -4545,7 +4545,7 @@
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T10:12:25.704447+00:00",
"lastTerminalAt": "2026-09-10T12:23:25.501701+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4556,31 +4556,6 @@
"total": 20,
"unresolvedFailureCount": 20
},
"hygon_k100-ai|llamacpp|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "llamacpp",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-07T23:53:16.902630+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -4614,16 +4589,17 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 5,
"ambiguous_runtime": 13,
"framework_architecture_unsupported": 4,
"model_load": 1,
"repository_structure": 1
"repository_structure": 1,
"runtime_memory": 1
},
"failureCount": 19,
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T10:21:30.006897+00:00",
"lastTerminalAt": "2026-09-10T12:23:25.501677+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4631,8 +4607,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 19,
"unresolvedFailureCount": 12
"total": 20,
"unresolvedFailureCount": 13
}
},
"recentProfileCombinationStats": {
@@ -4911,6 +4887,31 @@
"total": 2,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors": {
"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": "2026-09-10T12:23:25.501745+00:00",
"modelType": "gemma2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"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,
@@ -5885,9 +5886,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 33,
@@ -5900,8 +5901,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|28": {
"attributableFailureCount": 0,
@@ -7030,41 +7031,41 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1577,
"totalRecords": 1664,
"terminalRecords": 1583,
"totalRecords": 1670,
"totals": {
"attributableFailureCount": 413,
"decisionFailureRate": 0.8901,
"decisionSuccessRate": 0.1099,
"decisionTotal": 464,
"attributableFailureCount": 414,
"decisionFailureRate": 0.8903,
"decisionSuccessRate": 0.1097,
"decisionTotal": 465,
"failureBreakdown": {
"ambiguous_runtime": 339,
"ambiguous_runtime": 344,
"backend_operator": 35,
"framework_architecture_unsupported": 272,
"memory_capacity": 11,
"model_load": 47,
"platform_infrastructure": 3,
"repository_structure": 5,
"runtime_memory": 5,
"runtime_memory": 6,
"tokenizer_compatibility": 38,
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1526,
"failureRate": 0.9677,
"failureCount": 1532,
"failureRate": 0.9678,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 51,
"successRate": 0.0323,
"total": 1577,
"unresolvedFailureCount": 1110
"successRate": 0.0322,
"total": 1583,
"unresolvedFailureCount": 1115
},
"warnings": [
"GPU Cambricon_mlu-370-x8 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 Sunrise_pt-200-x1 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 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。",
@@ -7072,7 +7073,7 @@
"GPU hygon_k100-ai 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 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_mrv-100|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 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 Biren_166m|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -7093,6 +7094,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1664,
"summarizedRecords": 1670,
"version": 1
}