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

state: generation 11153 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-21 03:49:30 +00:00
parent 796025973c
commit c56e0479ef
9 changed files with 1711 additions and 1691 deletions
Download Patch File Download Diff File Expand all files Collapse all files

127
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T03:45:51.885355+00:00",
"lastSyncTime": "2026-09-21T03:45:50.542891+00:00",
"generatedAt": "2026-09-21T03:49:22.289651+00:00",
"lastSyncTime": "2026-09-21T03:49:21.585717+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -255,7 +255,7 @@
"ascend_910-b3|vllm|text-generation|model_type:qwen3_5": {
"architectureSignature": "model_type:qwen3_5",
"architectures": [],
"evidenceCount": 3,
"evidenceCount": 2,
"expiresAt": "2026-10-20T11:23:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-20T11:23:21+00:00",
@@ -264,13 +264,11 @@
"modelType": "qwen3_5",
"sourceModelIds": [
"logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired",
"ewinregirgojr/Qwen3.8-9B-Instruct-Turbo",
"ewinregirgojr/Qwen3.8-14B-Instruct-Turbo"
"ewinregirgojr/Qwen3.8-9B-Instruct-Turbo"
],
"sourceTaskIds": [
"4523512",
"4464446",
"4490182"
"4464446"
],
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation"
@@ -4442,7 +4440,7 @@
"decisionSuccessRate": 0.2299,
"decisionTotal": 87,
"failureBreakdown": {
"ambiguous_runtime": 60,
"ambiguous_runtime": 61,
"backend_operator": 8,
"framework_architecture_unsupported": 49,
"memory_capacity": 1,
@@ -4452,18 +4450,18 @@
"tokenizer_compatibility": 1,
"参数/模板问题": 12
},
"failureCount": 139,
"failureRate": 0.8742,
"failureCount": 140,
"failureRate": 0.875,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 20,
"successRate": 0.1258,
"successRate": 0.125,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 159,
"unresolvedFailureCount": 72
"total": 160,
"unresolvedFailureCount": 73
},
"Mthreads_s4000|vllm|visual-multi-modal": {
"attributableFailureCount": 1,
@@ -5089,7 +5087,7 @@
"decisionSuccessRate": 0.0231,
"decisionTotal": 3589,
"failureBreakdown": {
"ambiguous_runtime": 1462,
"ambiguous_runtime": 1463,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
@@ -5103,15 +5101,15 @@
"tokenizer_compatibility": 410,
"参数/模板问题": 41
},
"failureCount": 5873,
"failureCount": 5874,
"failureRate": 0.9861,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 864,
"successCount": 83,
"successRate": 0.0139,
"total": 5956,
"unresolvedFailureCount": 1503
"total": 5957,
"unresolvedFailureCount": 1504
},
"vllm-customized": {
"attributableFailureCount": 2,
@@ -5249,7 +5247,7 @@
"unresolvedFailureCount": 60
}
},
"generatedAt": "2026-09-21T03:45:51.875473+00:00",
"generatedAt": "2026-09-21T03:49:22.279754+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 90,
@@ -5551,7 +5549,7 @@
"decisionSuccessRate": 0.3604,
"decisionTotal": 111,
"failureBreakdown": {
"ambiguous_runtime": 106,
"ambiguous_runtime": 107,
"backend_operator": 8,
"framework_architecture_unsupported": 50,
"memory_capacity": 1,
@@ -5563,15 +5561,15 @@
"日志缺失": 96,
"验证失败": 26
},
"failureCount": 355,
"failureRate": 0.8987,
"failureCount": 356,
"failureRate": 0.899,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 40,
"successRate": 0.1013,
"total": 395,
"unresolvedFailureCount": 284
"successRate": 0.101,
"total": 396,
"unresolvedFailureCount": 285
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 732,
@@ -12559,9 +12557,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "lfm2",
@@ -12573,8 +12571,8 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Mthreads_s4000|vllm|text-generation|llama|awq": {
"attributableFailureCount": 0,
@@ -13897,18 +13895,18 @@
"unresolvedFailureCount": 10
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 7,
"consecutiveFailures": 7,
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 5,
"framework_architecture_unsupported": 6,
"framework_architecture_unsupported": 5,
"tokenizer_compatibility": 1
},
"failureCount": 12,
"failureCount": 11,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -13920,7 +13918,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 12,
"total": 11,
"unresolvedFailureCount": 5
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
@@ -14505,12 +14503,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 3,
"ambiguous_runtime": 4,
"backend_operator": 2,
"framework_architecture_unsupported": 4,
"runtime_memory": 1
},
"failureCount": 10,
"failureCount": 11,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -14522,8 +14520,8 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 10,
"unresolvedFailureCount": 3
"total": 11,
"unresolvedFailureCount": 4
},
"Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -18237,6 +18235,31 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|lfm2|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-21T03:49:21.585693+00:00",
"modelType": "lfm2",
"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|sophia_hybrid|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -28519,9 +28542,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 29,
@@ -28534,8 +28557,8 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Mthreads_s4000|vllm|text-generation|llama|awq|30": {
"attributableFailureCount": 0,
@@ -30373,15 +30396,15 @@
"unresolvedFailureCount": 1
}
},
"terminalRecords": 16071,
"totalRecords": 16248,
"terminalRecords": 16072,
"totalRecords": 16249,
"totals": {
"attributableFailureCount": 5836,
"decisionFailureRate": 0.8617,
"decisionSuccessRate": 0.1383,
"decisionTotal": 6773,
"failureBreakdown": {
"ambiguous_runtime": 3843,
"ambiguous_runtime": 3844,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 102,
@@ -30397,31 +30420,31 @@
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 15134,
"failureCount": 15135,
"failureRate": 0.9417,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 922,
"successCount": 937,
"successRate": 0.0583,
"total": 16071,
"unresolvedFailureCount": 8376
"total": 16072,
"unresolvedFailureCount": 8377
},
"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。",
@@ -30458,6 +30481,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16248,
"summarizedRecords": 16249,
"version": 1
}