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

state: generation 11353 (intent)

Browse Source
This commit is contained in:
CoolBoy
2026-09-21 09:02:20 +00:00
parent 3913cc4c6a
commit 39dfc07c33
7 changed files with 2703 additions and 2643 deletions
Download Patch File Download Diff File Expand all files Collapse all files

184
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T08:44:12.166191+00:00",
"lastSyncTime": "2026-09-21T08:44:09.587595+00:00",
"generatedAt": "2026-09-21T09:00:36.141304+00:00",
"lastSyncTime": "2026-09-21T09:00:33.862683+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3212,23 +3212,23 @@
"decisionSuccessRate": 0.5,
"decisionTotal": 16,
"failureBreakdown": {
"ambiguous_runtime": 16,
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 7,
"model_load": 1,
"验证失败": 1
},
"failureCount": 25,
"failureRate": 0.7576,
"failureCount": 26,
"failureRate": 0.7647,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 8,
"successRate": 0.2424,
"successRate": 0.2353,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 33,
"unresolvedFailureCount": 17
"total": 34,
"unresolvedFailureCount": 18
},
"Cambricon_mlu-370-x4|vllm|text-generation": {
"attributableFailureCount": 3,
@@ -4655,7 +4655,7 @@
"decisionSuccessRate": 0.2444,
"decisionTotal": 90,
"failureBreakdown": {
"ambiguous_runtime": 64,
"ambiguous_runtime": 65,
"backend_operator": 8,
"framework_architecture_unsupported": 50,
"memory_capacity": 1,
@@ -4665,18 +4665,18 @@
"tokenizer_compatibility": 1,
"参数/模板问题": 12
},
"failureCount": 144,
"failureRate": 0.8675,
"failureCount": 145,
"failureRate": 0.8683,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 22,
"successRate": 0.1325,
"successRate": 0.1317,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 166,
"unresolvedFailureCount": 76
"total": 167,
"unresolvedFailureCount": 77
},
"Mthreads_s4000|vllm|visual-multi-modal": {
"attributableFailureCount": 1,
@@ -5303,7 +5303,7 @@
"decisionSuccessRate": 0.0238,
"decisionTotal": 3608,
"failureBreakdown": {
"ambiguous_runtime": 1475,
"ambiguous_runtime": 1476,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
@@ -5317,15 +5317,15 @@
"tokenizer_compatibility": 411,
"参数/模板问题": 41
},
"failureCount": 5903,
"failureCount": 5904,
"failureRate": 0.9856,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 865,
"successCount": 86,
"successRate": 0.0144,
"total": 5989,
"unresolvedFailureCount": 1516
"total": 5990,
"unresolvedFailureCount": 1517
},
"vllm-customized": {
"attributableFailureCount": 3,
@@ -5353,22 +5353,22 @@
"decisionSuccessRate": 0.4878,
"decisionTotal": 41,
"failureBreakdown": {
"ambiguous_runtime": 53,
"ambiguous_runtime": 54,
"framework_architecture_unsupported": 18,
"model_load": 2,
"tokenizer_compatibility": 1,
"参数/模板问题": 3,
"验证失败": 1
},
"failureCount": 78,
"failureRate": 0.7959,
"failureCount": 79,
"failureRate": 0.798,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 20,
"successRate": 0.2041,
"total": 98,
"unresolvedFailureCount": 57
"successRate": 0.202,
"total": 99,
"unresolvedFailureCount": 58
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 27,
@@ -5468,7 +5468,7 @@
"unresolvedFailureCount": 70
}
},
"generatedAt": "2026-09-21T08:44:12.154585+00:00",
"generatedAt": "2026-09-21T09:00:36.130088+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 91,
@@ -5560,7 +5560,7 @@
"decisionSuccessRate": 0.0925,
"decisionTotal": 789,
"failureBreakdown": {
"ambiguous_runtime": 432,
"ambiguous_runtime": 433,
"architecture_compatibility": 53,
"context_length": 48,
"framework_architecture_unsupported": 272,
@@ -5573,15 +5573,15 @@
"日志缺失": 13,
"验证失败": 40
},
"failureCount": 1500,
"failureCount": 1501,
"failureRate": 0.9536,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 15,
"successCount": 73,
"successRate": 0.0464,
"total": 1573,
"unresolvedFailureCount": 769
"total": 1574,
"unresolvedFailureCount": 770
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 44,
@@ -5771,7 +5771,7 @@
"decisionSuccessRate": 0.3684,
"decisionTotal": 114,
"failureBreakdown": {
"ambiguous_runtime": 110,
"ambiguous_runtime": 111,
"backend_operator": 8,
"framework_architecture_unsupported": 51,
"memory_capacity": 1,
@@ -5783,15 +5783,15 @@
"日志缺失": 96,
"验证失败": 26
},
"failureCount": 360,
"failureRate": 0.8955,
"failureCount": 361,
"failureRate": 0.8958,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 42,
"successRate": 0.1045,
"total": 402,
"unresolvedFailureCount": 288
"successRate": 0.1042,
"total": 403,
"unresolvedFailureCount": 289
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 732,
@@ -8223,6 +8223,29 @@
"total": 5,
"unresolvedFailureCount": 5
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|minicpm|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "minicpm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|mpt|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -13808,6 +13831,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|granite|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "granite",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|lfm2|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -23021,6 +23067,30 @@
"total": 4,
"unresolvedFailureCount": 4
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|minicpm|none|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 33,
"modelType": "minicpm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|mpt|none|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -31119,6 +31189,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|granite|none|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
"modelType": "granite",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|lfm2|none|29": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -33215,15 +33309,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16192,
"totalRecords": 16375,
"terminalRecords": 16194,
"totalRecords": 16377,
"totals": {
"attributableFailureCount": 5862,
"decisionFailureRate": 0.8614,
"decisionSuccessRate": 0.1386,
"decisionTotal": 6805,
"failureBreakdown": {
"ambiguous_runtime": 3899,
"ambiguous_runtime": 3901,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 102,
@@ -33239,31 +33333,31 @@
"日志缺失": 719,
"验证失败": 674
},
"failureCount": 15249,
"failureCount": 15251,
"failureRate": 0.9418,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 924,
"successCount": 943,
"successRate": 0.0582,
"total": 16192,
"unresolvedFailureCount": 8463
"total": 16194,
"unresolvedFailureCount": 8465
},
"warnings": [
"GPU Iluvatar_mrv-100 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 Cambricon_mlu-370-x8 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 MetaX_c-500 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 Iluvatar_bi-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 Ascend_910-b3 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 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 hygon_k100-ai 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。",
"组合 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Sunrise_pt-200-x1|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。",
"组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -33303,6 +33397,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16375,
"summarizedRecords": 16377,
"version": 1
}