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

state: generation 11052 (intent)

Browse Source
This commit is contained in:
CoolBoy
2026-09-21 01:09:52 +00:00
parent ae80fd5ca5
commit 178bbd87fa
8 changed files with 2701 additions and 2617 deletions
Download Patch File Download Diff File Expand all files Collapse all files

260
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T00:42:11.581541+00:00",
"lastSyncTime": "2026-09-21T00:42:10.765072+00:00",
"generatedAt": "2026-09-21T01:08:25.997661+00:00",
"lastSyncTime": "2026-09-21T01:08:25.664348+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2475,20 +2475,21 @@
"failureBreakdown": {
"ambiguous_runtime": 13,
"framework_architecture_unsupported": 24,
"memory_capacity": 1
"memory_capacity": 1,
"参数/模板问题": 8
},
"failureCount": 38,
"failureRate": 0.95,
"failureCount": 46,
"failureRate": 0.9583,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.05,
"successRate": 0.0417,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 40,
"unresolvedFailureCount": 13
"total": 48,
"unresolvedFailureCount": 21
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 61,
@@ -2778,23 +2779,23 @@
"decisionSuccessRate": 0.2778,
"decisionTotal": 54,
"failureBreakdown": {
"ambiguous_runtime": 6,
"ambiguous_runtime": 7,
"framework_architecture_unsupported": 28,
"model_load": 9,
"tokenizer_compatibility": 2
},
"failureCount": 45,
"failureRate": 0.75,
"failureCount": 46,
"failureRate": 0.7541,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 15,
"successRate": 0.25,
"successRate": 0.2459,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 60,
"unresolvedFailureCount": 6
"total": 61,
"unresolvedFailureCount": 7
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 695,
@@ -4943,7 +4944,7 @@
"decisionSuccessRate": 0.0232,
"decisionTotal": 3580,
"failureBreakdown": {
"ambiguous_runtime": 1455,
"ambiguous_runtime": 1456,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
@@ -4957,15 +4958,15 @@
"tokenizer_compatibility": 410,
"参数/模板问题": 40
},
"failureCount": 5856,
"failureCount": 5857,
"failureRate": 0.986,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 864,
"successCount": 83,
"successRate": 0.014,
"total": 5939,
"unresolvedFailureCount": 1495
"total": 5940,
"unresolvedFailureCount": 1496
},
"vllm-customized": {
"attributableFailureCount": 2,
@@ -5089,20 +5090,21 @@
"framework_architecture_unsupported": 47,
"memory_capacity": 1,
"model_load": 1,
"tokenizer_compatibility": 1
"tokenizer_compatibility": 1,
"参数/模板问题": 8
},
"failureCount": 89,
"failureRate": 0.978,
"failureCount": 97,
"failureRate": 0.9798,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.022,
"total": 91,
"unresolvedFailureCount": 39
"successRate": 0.0202,
"total": 99,
"unresolvedFailureCount": 47
}
},
"generatedAt": "2026-09-21T00:42:11.571796+00:00",
"generatedAt": "2026-09-21T01:08:25.987700+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 87,
@@ -5115,19 +5117,19 @@
"memory_capacity": 2,
"repository_structure": 1,
"tokenizer_compatibility": 2,
"参数/模板问题": 19,
"参数/模板问题": 27,
"日志缺失": 3,
"验证失败": 27
},
"failureCount": 207,
"failureRate": 0.9159,
"failureCount": 215,
"failureRate": 0.9188,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 19,
"successRate": 0.0841,
"total": 226,
"unresolvedFailureCount": 120
"successRate": 0.0812,
"total": 234,
"unresolvedFailureCount": 128
},
"Ascend_910-b4": {
"attributableFailureCount": 309,
@@ -5163,7 +5165,7 @@
"decisionSuccessRate": 0.1225,
"decisionTotal": 204,
"failureBreakdown": {
"ambiguous_runtime": 136,
"ambiguous_runtime": 137,
"backend_operator": 4,
"context_length": 10,
"framework_architecture_unsupported": 116,
@@ -5177,15 +5179,15 @@
"日志缺失": 62,
"验证失败": 27
},
"failureCount": 620,
"failureRate": 0.9612,
"failureCount": 621,
"failureRate": 0.9613,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 25,
"successRate": 0.0388,
"total": 645,
"unresolvedFailureCount": 439
"successRate": 0.0387,
"total": 646,
"unresolvedFailureCount": 440
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 711,
@@ -6729,6 +6731,29 @@
"total": 5,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm|text-generation|llama|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 0.2,
@@ -13410,15 +13435,16 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 10,
"failureBreakdown": {
"ambiguous_runtime": 6,
"ambiguous_runtime": 5,
"framework_architecture_unsupported": 9,
"memory_capacity": 1
"memory_capacity": 1,
"参数/模板问题": 5
},
"failureCount": 16,
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-20T22:43:47.754995+00:00",
"lastTerminalAt": "2026-09-21T01:08:25.664296+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -13426,8 +13452,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 16,
"unresolvedFailureCount": 6
"total": 20,
"unresolvedFailureCount": 10
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 9,
@@ -13569,13 +13595,13 @@
"decisionSuccessRate": 0.1429,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 5,
"ambiguous_runtime": 6,
"framework_architecture_unsupported": 3,
"model_load": 2,
"tokenizer_compatibility": 1
},
"failureCount": 11,
"failureRate": 0.9167,
"failureCount": 12,
"failureRate": 0.9231,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T00:42:10.765041+00:00",
@@ -13583,11 +13609,11 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0833,
"successRate": 0.0769,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 12,
"unresolvedFailureCount": 5
"total": 13,
"unresolvedFailureCount": 6
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 2,
@@ -13829,18 +13855,18 @@
"unresolvedFailureCount": 1
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 3,
"attributableFailureCount": 2,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.4286,
"decisionSuccessRate": 0.5714,
"decisionTotal": 7,
"decisionFailureRate": 0.3333,
"decisionSuccessRate": 0.6667,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 3
"framework_architecture_unsupported": 2
},
"failureCount": 4,
"failureRate": 0.5,
"failureCount": 3,
"failureRate": 0.4286,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-18T11:36:11.987002+00:00",
@@ -13848,10 +13874,10 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 4,
"successRate": 0.5,
"successRate": 0.5714,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 8,
"total": 7,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -14089,47 +14115,20 @@
"unresolvedFailureCount": 1
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"decisionTotal": 4,
"failureBreakdown": {
"framework_architecture_unsupported": 1,
"platform_infrastructure": 3,
"tokenizer_compatibility": 5
"tokenizer_compatibility": 4
},
"failureCount": 9,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": "2026-09-16T02:03:21+00:00",
"lastTerminalAt": "2026-09-19T23:13:47.695526+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 9,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"backend_operator": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-16T01:44:44.924001+00:00",
"lastTerminalAt": "2026-09-19T23:13:47.695526+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -14137,7 +14136,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"total": 4,
"unresolvedFailureCount": 0
},
"Vastai_va16|unknown|text-generation": {
@@ -14173,10 +14172,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 14,
"ambiguous_runtime": 13,
"framework_architecture_unsupported": 6
},
"failureCount": 20,
"failureCount": 19,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -14188,8 +14187,8 @@
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 14
"total": 19,
"unresolvedFailureCount": 13
},
"hygon_k100-ai|llamacpp|text-generation": {
"attributableFailureCount": 0,
@@ -14998,6 +14997,31 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-21T01:08:25.664308+00:00",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm|text-generation|mistral|compressed-tensors": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -19373,6 +19397,30 @@
"total": 4,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|llama|compressed-tensors|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": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm|text-generation|llama|none|30": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -29112,15 +29160,15 @@
"unresolvedFailureCount": 1
}
},
"terminalRecords": 16010,
"totalRecords": 16174,
"terminalRecords": 16019,
"totalRecords": 16183,
"totals": {
"attributableFailureCount": 5821,
"decisionFailureRate": 0.862,
"decisionSuccessRate": 0.138,
"decisionTotal": 6753,
"failureBreakdown": {
"ambiguous_runtime": 3831,
"ambiguous_runtime": 3832,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 102,
@@ -29132,19 +29180,19 @@
"repository_structure": 734,
"runtime_memory": 83,
"tokenizer_compatibility": 659,
"参数/模板问题": 3112,
"参数/模板问题": 3120,
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 15078,
"failureCount": 15087,
"failureRate": 0.9418,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 922,
"successCount": 932,
"successRate": 0.0582,
"total": 16010,
"unresolvedFailureCount": 8335
"total": 16019,
"unresolvedFailureCount": 8344
},
"warnings": [
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -29191,12 +29239,12 @@
"组合 Cambricon_mlu-370-x4|unknown|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 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。",
"组合 Iluvatar_bi-150|transformers|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|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-x8|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 Ascend_910-b3|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-x8|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 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16174,
"summarizedRecords": 16183,
"version": 1
}