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

state: generation 18911 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-30 19:28:56 +00:00
parent 09eb1a000e
commit 03f1e2c383
8 changed files with 1247 additions and 1248 deletions
Download Patch File Download Diff File Expand all files Collapse all files

100
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-30T17:21:20.789157+00:00",
"lastSyncTime": "2026-09-30T17:21:20.559656+00:00",
"generatedAt": "2026-09-30T19:26:29.815070+00:00",
"lastSyncTime": "2026-09-30T19:26:29.545477+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3901,29 +3901,29 @@
"unresolvedFailureCount": 4
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation": {
"attributableFailureCount": 17,
"decisionFailureRate": 0.6538,
"decisionSuccessRate": 0.3462,
"decisionTotal": 26,
"attributableFailureCount": 18,
"decisionFailureRate": 0.6667,
"decisionSuccessRate": 0.3333,
"decisionTotal": 27,
"failureBreakdown": {
"ambiguous_runtime": 44,
"framework_architecture_unsupported": 14,
"framework_architecture_unsupported": 15,
"model_load": 3,
"platform_infrastructure": 1,
"参数/模板问题": 1,
"验证失败": 3
},
"failureCount": 66,
"failureRate": 0.88,
"failureCount": 67,
"failureRate": 0.8816,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 9,
"successRate": 0.12,
"successRate": 0.1184,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 75,
"total": 76,
"unresolvedFailureCount": 48
},
"Cambricon_mlu-370-x4|vllm|text-generation": {
@@ -6072,27 +6072,27 @@
"unresolvedFailureCount": 51
},
"vllm-mlu": {
"attributableFailureCount": 31,
"decisionFailureRate": 0.5849,
"decisionSuccessRate": 0.4151,
"decisionTotal": 53,
"attributableFailureCount": 32,
"decisionFailureRate": 0.5926,
"decisionSuccessRate": 0.4074,
"decisionTotal": 54,
"failureBreakdown": {
"ambiguous_runtime": 93,
"framework_architecture_unsupported": 25,
"framework_architecture_unsupported": 26,
"model_load": 5,
"platform_infrastructure": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 4,
"验证失败": 3
},
"failureCount": 132,
"failureRate": 0.8571,
"failureCount": 133,
"failureRate": 0.8581,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 22,
"successRate": 0.1429,
"total": 154,
"successRate": 0.1419,
"total": 155,
"unresolvedFailureCount": 100
},
"vllm-patch-tokenizer": {
@@ -6196,7 +6196,7 @@
"unresolvedFailureCount": 217
}
},
"generatedAt": "2026-09-30T17:21:20.773013+00:00",
"generatedAt": "2026-09-30T19:26:29.802975+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 109,
@@ -6284,15 +6284,15 @@
"unresolvedFailureCount": 561
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 750,
"decisionFailureRate": 0.9102,
"decisionSuccessRate": 0.0898,
"decisionTotal": 824,
"attributableFailureCount": 751,
"decisionFailureRate": 0.9103,
"decisionSuccessRate": 0.0897,
"decisionTotal": 825,
"failureBreakdown": {
"ambiguous_runtime": 509,
"architecture_compatibility": 53,
"context_length": 48,
"framework_architecture_unsupported": 303,
"framework_architecture_unsupported": 304,
"memory_capacity": 219,
"model_load": 7,
"platform_infrastructure": 16,
@@ -6302,14 +6302,14 @@
"日志缺失": 13,
"验证失败": 42
},
"failureCount": 1617,
"failureRate": 0.9562,
"failureCount": 1618,
"failureRate": 0.9563,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 16,
"successCount": 74,
"successRate": 0.0438,
"total": 1691,
"successRate": 0.0437,
"total": 1692,
"unresolvedFailureCount": 851
},
"Cambricon_mlu-370-x8": {
@@ -11328,14 +11328,14 @@
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 3,
"attributableFailureCount": 4,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 4,
"failureBreakdown": {
"framework_architecture_unsupported": 3
"framework_architecture_unsupported": 4
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "qwen3_5_moe",
@@ -11347,7 +11347,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 3,
"total": 4,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_text|none": {
@@ -35160,14 +35160,14 @@
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_moe|none|33": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 33,
@@ -35180,7 +35180,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_moe|none|34": {
@@ -53813,20 +53813,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17167,
"totalRecords": 17388,
"terminalRecords": 17168,
"totalRecords": 17389,
"totals": {
"attributableFailureCount": 6152,
"attributableFailureCount": 6153,
"decisionFailureRate": 0.8632,
"decisionSuccessRate": 0.1368,
"decisionTotal": 7127,
"decisionTotal": 7128,
"failureBreakdown": {
"ambiguous_runtime": 4474,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
"context_length": 326,
"framework_architecture_unsupported": 2199,
"framework_architecture_unsupported": 2200,
"memory_capacity": 1206,
"model_load": 550,
"platform_infrastructure": 943,
@@ -53837,30 +53837,30 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16192,
"failureCount": 16193,
"failureRate": 0.9432,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 943,
"successCount": 975,
"successRate": 0.0568,
"total": 17167,
"total": 17168,
"unresolvedFailureCount": 9097
},
"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。",
@@ -53905,6 +53905,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17388,
"summarizedRecords": 17389,
"version": 1
}