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

state: generation 18776 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-30 11:57:25 +00:00
parent 08c9c988d3
commit 40cdc3c7fc
9 changed files with 1426 additions and 1453 deletions
Download Patch File Download Diff File Expand all files Collapse all files

183
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-30T11:45:44.518068+00:00",
"lastSyncTime": "2026-09-30T11:45:44.243364+00:00",
"generatedAt": "2026-09-30T11:55:48.738682+00:00",
"lastSyncTime": "2026-09-30T11:55:48.444086+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3448,25 +3448,25 @@
"decisionSuccessRate": 0.0952,
"decisionTotal": 42,
"failureBreakdown": {
"ambiguous_runtime": 69,
"ambiguous_runtime": 70,
"context_length": 7,
"framework_architecture_unsupported": 30,
"memory_capacity": 1,
"platform_infrastructure": 1,
"参数/模板问题": 8
},
"failureCount": 116,
"failureRate": 0.9667,
"failureCount": 117,
"failureRate": 0.9669,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 4,
"successRate": 0.0333,
"successRate": 0.0331,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 120,
"unresolvedFailureCount": 77
"total": 121,
"unresolvedFailureCount": 78
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 69,
@@ -5367,9 +5367,9 @@
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 76,
"decisionFailureRate": 0.7677,
"decisionSuccessRate": 0.2323,
"decisionTotal": 99,
"decisionFailureRate": 0.76,
"decisionSuccessRate": 0.24,
"decisionTotal": 100,
"failureBreakdown": {
"ambiguous_runtime": 75,
"attention_backend": 2,
@@ -5384,16 +5384,16 @@
"参数/模板问题": 12
},
"failureCount": 164,
"failureRate": 0.877,
"failureRate": 0.8723,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 23,
"successRate": 0.123,
"successCount": 24,
"successRate": 0.1277,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 187,
"total": 188,
"unresolvedFailureCount": 87
},
"Mthreads_s4000|vllm|visual-multi-modal": {
@@ -6019,9 +6019,9 @@
},
"vllm": {
"attributableFailureCount": 3633,
"decisionFailureRate": 0.973,
"decisionSuccessRate": 0.027,
"decisionTotal": 3734,
"decisionFailureRate": 0.9727,
"decisionSuccessRate": 0.0273,
"decisionTotal": 3735,
"failureBreakdown": {
"ambiguous_runtime": 1589,
"architecture_compatibility": 112,
@@ -6038,13 +6038,13 @@
"参数/模板问题": 50
},
"failureCount": 6145,
"failureRate": 0.9838,
"failureRate": 0.9837,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 873,
"successCount": 101,
"successRate": 0.0162,
"total": 6246,
"successCount": 102,
"successRate": 0.0163,
"total": 6247,
"unresolvedFailureCount": 1639
},
"vllm-customized": {
@@ -6172,7 +6172,7 @@
"decisionSuccessRate": 0.0685,
"decisionTotal": 146,
"failureBreakdown": {
"ambiguous_runtime": 181,
"ambiguous_runtime": 182,
"backend_operator": 15,
"context_length": 7,
"framework_architecture_unsupported": 81,
@@ -6184,18 +6184,18 @@
"tokenizer_compatibility": 2,
"参数/模板问题": 29
},
"failureCount": 349,
"failureRate": 0.9721,
"failureCount": 350,
"failureRate": 0.9722,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 10,
"successRate": 0.0279,
"total": 359,
"unresolvedFailureCount": 210
"successRate": 0.0278,
"total": 360,
"unresolvedFailureCount": 211
}
},
"generatedAt": "2026-09-30T11:45:44.505405+00:00",
"generatedAt": "2026-09-30T11:55:48.725990+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 108,
@@ -6203,7 +6203,7 @@
"decisionSuccessRate": 0.1692,
"decisionTotal": 130,
"failureBreakdown": {
"ambiguous_runtime": 137,
"ambiguous_runtime": 138,
"context_length": 7,
"framework_architecture_unsupported": 95,
"memory_capacity": 2,
@@ -6214,15 +6214,15 @@
"日志缺失": 3,
"验证失败": 27
},
"failureCount": 315,
"failureRate": 0.9347,
"failureCount": 316,
"failureRate": 0.9349,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 22,
"successRate": 0.0653,
"total": 337,
"unresolvedFailureCount": 206
"successRate": 0.0651,
"total": 338,
"unresolvedFailureCount": 207
},
"Ascend_910-b4": {
"attributableFailureCount": 325,
@@ -6502,9 +6502,9 @@
},
"Mthreads_s4000": {
"attributableFailureCount": 80,
"decisionFailureRate": 0.6452,
"decisionSuccessRate": 0.3548,
"decisionTotal": 124,
"decisionFailureRate": 0.64,
"decisionSuccessRate": 0.36,
"decisionTotal": 125,
"failureBreakdown": {
"ambiguous_runtime": 121,
"attention_backend": 2,
@@ -6521,13 +6521,13 @@
"验证失败": 26
},
"failureCount": 380,
"failureRate": 0.8962,
"failureRate": 0.8941,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 44,
"successRate": 0.1038,
"total": 424,
"successCount": 45,
"successRate": 0.1059,
"total": 425,
"unresolvedFailureCount": 299
},
"Sunrise_pt-200-x1": {
@@ -6893,10 +6893,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 11,
"ambiguous_runtime": 12,
"context_length": 5
},
"failureCount": 16,
"failureCount": 17,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "llama",
@@ -6908,8 +6908,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 16,
"unresolvedFailureCount": 11
"total": 17,
"unresolvedFailureCount": 12
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|none": {
"attributableFailureCount": 0,
@@ -20957,7 +20957,7 @@
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
@@ -20967,11 +20967,11 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 1,
"successCount": 2,
"successRate": 1.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|qwen3_5_moe|modelopt": {
@@ -23576,11 +23576,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 3,
"ambiguous_runtime": 4,
"context_length": 1,
"framework_architecture_unsupported": 1
},
"failureCount": 5,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastPlatformFailureAt": null,
@@ -23592,8 +23592,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 3
"total": 6,
"unresolvedFailureCount": 4
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 2,
@@ -24194,31 +24194,6 @@
"total": 20,
"unresolvedFailureCount": 4
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T02:58:30.354826+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 3,
"consecutiveFailures": 3,
@@ -24408,10 +24383,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 1,
"ambiguous_runtime": 2,
"context_length": 1
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-30T11:45:44.243364+00:00",
@@ -24424,8 +24399,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 1
"total": 3,
"unresolvedFailureCount": 2
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|phi3small|compressed-tensors": {
"attributableFailureCount": 1,
@@ -28060,9 +28035,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 6
"ambiguous_runtime": 7
},
"failureCount": 6,
"failureCount": 7,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 33,
@@ -28075,8 +28050,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 6,
"unresolvedFailureCount": 6
"total": 7,
"unresolvedFailureCount": 7
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|35": {
"attributableFailureCount": 0,
@@ -49578,7 +49553,7 @@
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
@@ -49589,11 +49564,11 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 1,
"successCount": 2,
"successRate": 1.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|qwen3_5_moe|modelopt|34": {
@@ -53555,15 +53530,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17152,
"totalRecords": 17373,
"terminalRecords": 17154,
"totalRecords": 17375,
"totals": {
"attributableFailureCount": 6147,
"decisionFailureRate": 0.8633,
"decisionSuccessRate": 0.1367,
"decisionTotal": 7120,
"decisionFailureRate": 0.8632,
"decisionSuccessRate": 0.1368,
"decisionTotal": 7121,
"failureBreakdown": {
"ambiguous_runtime": 4466,
"ambiguous_runtime": 4467,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
@@ -53579,30 +53554,30 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16179,
"failureRate": 0.9433,
"failureCount": 16180,
"failureRate": 0.9432,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 943,
"successCount": 973,
"successRate": 0.0567,
"total": 17152,
"unresolvedFailureCount": 9089
"successCount": 974,
"successRate": 0.0568,
"total": 17154,
"unresolvedFailureCount": 9090
},
"warnings": [
"GPU Iluvatar_mrv-100 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 Biren_166m 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 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 hygon_k100-ai 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 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 Vastai_va16 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 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 Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
"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 Kunlunxin_p-800|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。",
@@ -53646,6 +53621,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17373,
"summarizedRecords": 17375,
"version": 1
}