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

state: generation 8406 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-16 21:53:28 +00:00
parent bb462abac9
commit 7ef333737d
10 changed files with 1924 additions and 1925 deletions
Download Patch File Download Diff File Expand all files Collapse all files

138
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-16T21:42:45.309128+00:00",
"lastSyncTime": "2026-09-16T21:42:43.203719+00:00",
"generatedAt": "2026-09-16T21:51:28.894307+00:00",
"lastSyncTime": "2026-09-16T21:51:28.830536+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2478,9 +2478,9 @@
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 42,
"decisionFailureRate": 0.8936,
"decisionSuccessRate": 0.1064,
"decisionTotal": 47,
"decisionFailureRate": 0.875,
"decisionSuccessRate": 0.125,
"decisionTotal": 48,
"failureBreakdown": {
"ambiguous_runtime": 42,
"backend_operator": 4,
@@ -2493,16 +2493,16 @@
"参数/模板问题": 3
},
"failureCount": 87,
"failureRate": 0.9457,
"failureRate": 0.9355,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 5,
"successRate": 0.0543,
"successCount": 6,
"successRate": 0.0645,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 92,
"total": 93,
"unresolvedFailureCount": 45
},
"Sunrise_pt-200-x1|unknown|text-generation": {
@@ -2583,22 +2583,22 @@
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 14,
"decisionTotal": 15,
"failureBreakdown": {
"参数/模板问题": 15,
"验证失败": 130
},
"failureCount": 145,
"failureRate": 0.9119,
"failureRate": 0.9062,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 14,
"successRate": 0.0881,
"successCount": 15,
"successRate": 0.0938,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 159,
"total": 160,
"unresolvedFailureCount": 145
},
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
@@ -2782,9 +2782,9 @@
},
"unknown": {
"attributableFailureCount": 185,
"decisionFailureRate": 0.746,
"decisionSuccessRate": 0.254,
"decisionTotal": 248,
"decisionFailureRate": 0.743,
"decisionSuccessRate": 0.257,
"decisionTotal": 249,
"failureBreakdown": {
"ambiguous_runtime": 157,
"backend_operator": 4,
@@ -2798,20 +2798,20 @@
"验证失败": 673
},
"failureCount": 1089,
"failureRate": 0.9453,
"failureRate": 0.9445,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 63,
"successRate": 0.0547,
"total": 1152,
"successCount": 64,
"successRate": 0.0555,
"total": 1153,
"unresolvedFailureCount": 903
},
"vllm": {
"attributableFailureCount": 379,
"decisionFailureRate": 0.9619,
"decisionSuccessRate": 0.0381,
"decisionTotal": 394,
"decisionFailureRate": 0.9595,
"decisionSuccessRate": 0.0405,
"decisionTotal": 395,
"failureBreakdown": {
"ambiguous_runtime": 222,
"backend_operator": 35,
@@ -2825,13 +2825,13 @@
"参数/模板问题": 31
},
"failureCount": 634,
"failureRate": 0.9769,
"failureRate": 0.9754,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 15,
"successRate": 0.0231,
"total": 649,
"successCount": 16,
"successRate": 0.0246,
"total": 650,
"unresolvedFailureCount": 253
},
"vllm-mlu": {
@@ -2943,7 +2943,7 @@
"unresolvedFailureCount": 6
}
},
"generatedAt": "2026-09-16T21:42:45.303114+00:00",
"generatedAt": "2026-09-16T21:51:28.887849+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 51,
@@ -3182,9 +3182,9 @@
},
"Mthreads_s4000": {
"attributableFailureCount": 43,
"decisionFailureRate": 0.86,
"decisionSuccessRate": 0.14,
"decisionTotal": 50,
"decisionFailureRate": 0.8431,
"decisionSuccessRate": 0.1569,
"decisionTotal": 51,
"failureBreakdown": {
"ambiguous_runtime": 42,
"backend_operator": 4,
@@ -3198,13 +3198,13 @@
"验证失败": 26
},
"failureCount": 122,
"failureRate": 0.9457,
"failureRate": 0.9385,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 7,
"successRate": 0.0543,
"total": 129,
"successCount": 8,
"successRate": 0.0615,
"total": 130,
"unresolvedFailureCount": 79
},
"Sunrise_pt-200-x1": {
@@ -3234,9 +3234,9 @@
},
"Vastai_va16": {
"attributableFailureCount": 60,
"decisionFailureRate": 0.8108,
"decisionSuccessRate": 0.1892,
"decisionTotal": 74,
"decisionFailureRate": 0.8,
"decisionSuccessRate": 0.2,
"decisionTotal": 75,
"failureBreakdown": {
"ambiguous_runtime": 68,
"framework_architecture_unsupported": 53,
@@ -3246,13 +3246,13 @@
"验证失败": 130
},
"failureCount": 273,
"failureRate": 0.9512,
"failureRate": 0.9479,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 14,
"successRate": 0.0488,
"total": 287,
"successCount": 15,
"successRate": 0.0521,
"total": 288,
"unresolvedFailureCount": 213
},
"hygon_k100-ai": {
@@ -5666,23 +5666,23 @@
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 3,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 0.25,
"failureRate": 0.2,
"framework": "vllm",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 3,
"successRate": 0.75,
"successCount": 4,
"successRate": 0.8,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 4,
"total": 5,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|nanbeige|compressed-tensors": {
@@ -6844,23 +6844,23 @@
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"参数/模板问题": 2
},
"failureCount": 2,
"failureRate": 0.6667,
"failureRate": 0.5,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-16T16:08:21.748740+00:00",
"lastTerminalAt": "2026-09-16T21:51:28.830496+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.3333,
"successCount": 2,
"successRate": 0.5,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 3,
"total": 4,
"unresolvedFailureCount": 2
},
"Vastai_va16|vllm|text-generation": {
@@ -10663,7 +10663,7 @@
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 3,
"decisionTotal": 4,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
@@ -10674,11 +10674,11 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 3,
"successCount": 4,
"successRate": 1.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 3,
"total": 4,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|llama|awq|33": {
@@ -11423,13 +11423,13 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2057,
"totalRecords": 2160,
"terminalRecords": 2059,
"totalRecords": 2162,
"totals": {
"attributableFailureCount": 669,
"decisionFailureRate": 0.892,
"decisionSuccessRate": 0.108,
"decisionTotal": 750,
"decisionFailureRate": 0.8896,
"decisionSuccessRate": 0.1104,
"decisionTotal": 752,
"failureBreakdown": {
"ambiguous_runtime": 500,
"backend_operator": 45,
@@ -11444,13 +11444,13 @@
"验证失败": 673
},
"failureCount": 1976,
"failureRate": 0.9606,
"failureRate": 0.9597,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 10,
"successCount": 81,
"successRate": 0.0394,
"total": 2057,
"successCount": 83,
"successRate": 0.0403,
"total": 2059,
"unresolvedFailureCount": 1297
},
"warnings": [
@@ -11461,11 +11461,11 @@
"GPU Biren_166m 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 hygon_k100-ai 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 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 Ascend_910-b3 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 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 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。",
"组合 Biren_166m|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 Vastai_va16|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。",
@@ -11490,6 +11490,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2160,
"summarizedRecords": 2162,
"version": 1
}