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

state: generation 19874 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-03 04:13:48 +00:00
parent 0b69dd5fbb
commit 399d2076b6
9 changed files with 1176 additions and 1177 deletions
Download Patch File Download Diff File Expand all files Collapse all files

122
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-02T23:59:53.483739+00:00",
"lastSyncTime": "2026-10-02T23:59:53.248046+00:00",
"generatedAt": "2026-10-03T04:11:25.408860+00:00",
"lastSyncTime": "2026-10-03T04:11:25.147559+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3903,29 +3903,29 @@
"unresolvedFailureCount": 4
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation": {
"attributableFailureCount": 21,
"decisionFailureRate": 0.7,
"decisionSuccessRate": 0.3,
"decisionTotal": 30,
"attributableFailureCount": 22,
"decisionFailureRate": 0.7097,
"decisionSuccessRate": 0.2903,
"decisionTotal": 31,
"failureBreakdown": {
"ambiguous_runtime": 46,
"framework_architecture_unsupported": 18,
"model_load": 3,
"model_load": 4,
"platform_infrastructure": 1,
"参数/模板问题": 1,
"验证失败": 3
},
"failureCount": 72,
"failureRate": 0.8889,
"failureCount": 73,
"failureRate": 0.8902,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 9,
"successRate": 0.1111,
"successRate": 0.1098,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 81,
"total": 82,
"unresolvedFailureCount": 50
},
"Cambricon_mlu-370-x4|vllm|text-generation": {
@@ -6074,27 +6074,27 @@
"unresolvedFailureCount": 51
},
"vllm-mlu": {
"attributableFailureCount": 37,
"decisionFailureRate": 0.6271,
"decisionSuccessRate": 0.3729,
"decisionTotal": 59,
"attributableFailureCount": 38,
"decisionFailureRate": 0.6333,
"decisionSuccessRate": 0.3667,
"decisionTotal": 60,
"failureBreakdown": {
"ambiguous_runtime": 97,
"framework_architecture_unsupported": 30,
"model_load": 6,
"model_load": 7,
"platform_infrastructure": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 4,
"验证失败": 3
},
"failureCount": 142,
"failureRate": 0.8659,
"failureCount": 143,
"failureRate": 0.8667,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 22,
"successRate": 0.1341,
"total": 164,
"successRate": 0.1333,
"total": 165,
"unresolvedFailureCount": 104
},
"vllm-patch-tokenizer": {
@@ -6198,7 +6198,7 @@
"unresolvedFailureCount": 230
}
},
"generatedAt": "2026-10-02T23:59:53.470898+00:00",
"generatedAt": "2026-10-03T04:11:25.395549+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 116,
@@ -6286,17 +6286,17 @@
"unresolvedFailureCount": 567
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 754,
"decisionFailureRate": 0.9106,
"decisionSuccessRate": 0.0894,
"decisionTotal": 828,
"attributableFailureCount": 755,
"decisionFailureRate": 0.9107,
"decisionSuccessRate": 0.0893,
"decisionTotal": 829,
"failureBreakdown": {
"ambiguous_runtime": 511,
"architecture_compatibility": 53,
"context_length": 48,
"framework_architecture_unsupported": 307,
"memory_capacity": 219,
"model_load": 7,
"model_load": 8,
"platform_infrastructure": 16,
"repository_structure": 85,
"tokenizer_compatibility": 35,
@@ -6304,14 +6304,14 @@
"日志缺失": 13,
"验证失败": 42
},
"failureCount": 1623,
"failureCount": 1624,
"failureRate": 0.9564,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 16,
"successCount": 74,
"successRate": 0.0436,
"total": 1697,
"total": 1698,
"unresolvedFailureCount": 853
},
"Cambricon_mlu-370-x8": {
@@ -11677,15 +11677,16 @@
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 8,
"attributableFailureCount": 1,
"decisionFailureRate": 0.1111,
"decisionSuccessRate": 0.8889,
"decisionTotal": 9,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 1,
"model_load": 1
},
"failureCount": 1,
"failureRate": 0.1111,
"failureCount": 2,
"failureRate": 0.2,
"framework": "vllm-mlu",
"modelType": "qwen3",
"pendingCount": 0,
@@ -11693,10 +11694,10 @@
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 8,
"successRate": 0.8889,
"successRate": 0.8,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 9,
"total": 10,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|sophia_hybrid|none": {
@@ -36481,15 +36482,16 @@
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 7,
"attributableFailureCount": 1,
"decisionFailureRate": 0.125,
"decisionSuccessRate": 0.875,
"decisionTotal": 8,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 1,
"model_load": 1
},
"failureCount": 1,
"failureRate": 0.125,
"failureCount": 2,
"failureRate": 0.2222,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 32,
"modelType": "qwen3",
@@ -36498,10 +36500,10 @@
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 7,
"successRate": 0.875,
"successRate": 0.7778,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 8,
"total": 9,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|sophia_hybrid|none|31": {
@@ -55475,13 +55477,13 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17251,
"totalRecords": 17472,
"terminalRecords": 17252,
"totalRecords": 17473,
"totals": {
"attributableFailureCount": 6187,
"decisionFailureRate": 0.8637,
"decisionSuccessRate": 0.1363,
"decisionTotal": 7163,
"attributableFailureCount": 6188,
"decisionFailureRate": 0.8638,
"decisionSuccessRate": 0.1362,
"decisionTotal": 7164,
"failureBreakdown": {
"ambiguous_runtime": 4518,
"architecture_compatibility": 212,
@@ -55490,7 +55492,7 @@
"context_length": 327,
"framework_architecture_unsupported": 2227,
"memory_capacity": 1206,
"model_load": 555,
"model_load": 556,
"platform_infrastructure": 947,
"repository_structure": 742,
"runtime_memory": 101,
@@ -55499,14 +55501,14 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16275,
"failureCount": 16276,
"failureRate": 0.9434,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 947,
"successCount": 976,
"successRate": 0.0566,
"total": 17251,
"total": 17252,
"unresolvedFailureCount": 9141
},
"warnings": [
@@ -55517,13 +55519,13 @@
"GPU hygon_k100-ai 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-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_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 Kunlunxin_p-800 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 Cambricon_mlu-370-x8 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 Iluvatar_bi-150 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。",
"组合 MetaX_c-500|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 Cambricon_mlu-370-x4|vllm-mlu|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-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -55567,6 +55569,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17472,
"summarizedRecords": 17473,
"version": 1
}