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

state: generation 9842 (intent)

Browse Source
This commit is contained in:
CoolBoy
2026-09-19 14:12:16 +00:00
parent e756ae1662
commit 0c28063b17
7 changed files with 867 additions and 843 deletions
Download Patch File Download Diff File Expand all files Collapse all files

178
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-19T13:54:57.226969+00:00",
"lastSyncTime": "2026-09-19T13:54:57.192288+00:00",
"generatedAt": "2026-09-19T14:10:52.788588+00:00",
"lastSyncTime": "2026-09-19T14:10:52.522734+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1856,9 +1856,9 @@
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 50,
"decisionFailureRate": 0.8475,
"decisionSuccessRate": 0.1525,
"decisionTotal": 59,
"decisionFailureRate": 0.8333,
"decisionSuccessRate": 0.1667,
"decisionTotal": 60,
"failureBreakdown": {
"ambiguous_runtime": 34,
"framework_architecture_unsupported": 48,
@@ -1866,16 +1866,16 @@
"tokenizer_compatibility": 1
},
"failureCount": 84,
"failureRate": 0.9032,
"failureRate": 0.8936,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 9,
"successRate": 0.0968,
"successCount": 10,
"successRate": 0.1064,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 93,
"total": 94,
"unresolvedFailureCount": 34
},
"Ascend_910-b4|llamacpp|text-generation": {
@@ -2745,18 +2745,18 @@
"unresolvedFailureCount": 29
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
"attributableFailureCount": 14,
"attributableFailureCount": 16,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 14,
"decisionTotal": 16,
"failureBreakdown": {
"ambiguous_runtime": 10,
"framework_architecture_unsupported": 10,
"model_load": 1,
"runtime_memory": 3,
"runtime_memory": 5,
"参数/模板问题": 8
},
"failureCount": 32,
"failureCount": 34,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"pendingCount": 0,
@@ -2766,7 +2766,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 32,
"total": 34,
"unresolvedFailureCount": 18
},
"hygon_k100-ai|vllm|text-generation": {
@@ -2863,9 +2863,9 @@
},
"vllm": {
"attributableFailureCount": 424,
"decisionFailureRate": 0.8689,
"decisionSuccessRate": 0.1311,
"decisionTotal": 488,
"decisionFailureRate": 0.8671,
"decisionSuccessRate": 0.1329,
"decisionTotal": 489,
"failureBreakdown": {
"ambiguous_runtime": 247,
"backend_operator": 40,
@@ -2879,13 +2879,13 @@
"参数/模板问题": 40
},
"failureCount": 713,
"failureRate": 0.9176,
"failureRate": 0.9165,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 64,
"successRate": 0.0824,
"total": 777,
"successCount": 65,
"successRate": 0.0835,
"total": 778,
"unresolvedFailureCount": 287
},
"vllm-mlu": {
@@ -2910,25 +2910,25 @@
"unresolvedFailureCount": 42
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 14,
"attributableFailureCount": 16,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 14,
"decisionTotal": 16,
"failureBreakdown": {
"ambiguous_runtime": 10,
"framework_architecture_unsupported": 10,
"model_load": 1,
"runtime_memory": 3,
"runtime_memory": 5,
"参数/模板问题": 8
},
"failureCount": 32,
"failureCount": 34,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 32,
"total": 34,
"unresolvedFailureCount": 18
},
"vllm_0_17_0_corex_4_4_0": {
@@ -2998,13 +2998,13 @@
"unresolvedFailureCount": 20
}
},
"generatedAt": "2026-09-19T13:54:57.221430+00:00",
"generatedAt": "2026-09-19T14:10:52.783219+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 62,
"decisionFailureRate": 0.8378,
"decisionSuccessRate": 0.1622,
"decisionTotal": 74,
"decisionFailureRate": 0.8267,
"decisionSuccessRate": 0.1733,
"decisionTotal": 75,
"failureBreakdown": {
"ambiguous_runtime": 40,
"framework_architecture_unsupported": 60,
@@ -3014,13 +3014,13 @@
"验证失败": 27
},
"failureCount": 139,
"failureRate": 0.9205,
"failureRate": 0.9145,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 12,
"successRate": 0.0795,
"total": 151,
"successCount": 13,
"successRate": 0.0855,
"total": 152,
"unresolvedFailureCount": 77
},
"Ascend_910-b4": {
@@ -3311,28 +3311,28 @@
"unresolvedFailureCount": 229
},
"hygon_k100-ai": {
"attributableFailureCount": 70,
"attributableFailureCount": 72,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 70,
"decisionTotal": 72,
"failureBreakdown": {
"ambiguous_runtime": 37,
"framework_architecture_unsupported": 54,
"memory_capacity": 1,
"model_load": 6,
"repository_structure": 4,
"runtime_memory": 5,
"runtime_memory": 7,
"参数/模板问题": 10,
"验证失败": 27
},
"failureCount": 144,
"failureCount": 146,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 144,
"total": 146,
"unresolvedFailureCount": 74
}
},
@@ -3610,7 +3610,7 @@
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
@@ -3620,11 +3620,11 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 2,
"successCount": 3,
"successRate": 1.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm|text-generation|muse_glimmer|none": {
@@ -7667,15 +7667,15 @@
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|awq": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 3,
"runtime_memory": 1
"runtime_memory": 2
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"modelType": "llama",
@@ -7687,19 +7687,20 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 4,
"total": 5,
"unresolvedFailureCount": 3
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|none": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 1,
"model_load": 1
"model_load": 1,
"runtime_memory": 1
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"modelType": "llama",
@@ -7711,7 +7712,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 1
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|nanbeige|compressed-tensors": {
@@ -9076,7 +9077,7 @@
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
@@ -9087,11 +9088,11 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 2,
"successCount": 3,
"successRate": 1.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm|text-generation|muse_glimmer|none|34": {
@@ -15392,6 +15393,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|awq|30": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"runtime_memory": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"loadSizeLog2Bucket": 30,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|awq|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -15442,14 +15467,15 @@
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 1,
"runtime_memory": 1
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"loadSizeLog2Bucket": 32,
@@ -15462,7 +15488,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 1
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|nanbeige|compressed-tensors|32": {
@@ -15707,13 +15733,13 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2337,
"totalRecords": 2440,
"terminalRecords": 2340,
"totalRecords": 2443,
"totals": {
"attributableFailureCount": 762,
"decisionFailureRate": 0.8176,
"decisionSuccessRate": 0.1824,
"decisionTotal": 932,
"attributableFailureCount": 764,
"decisionFailureRate": 0.8171,
"decisionSuccessRate": 0.1829,
"decisionTotal": 935,
"failureBreakdown": {
"ambiguous_runtime": 588,
"backend_operator": 55,
@@ -15722,23 +15748,23 @@
"model_load": 89,
"platform_infrastructure": 11,
"repository_structure": 8,
"runtime_memory": 20,
"runtime_memory": 22,
"tokenizer_compatibility": 66,
"参数/模板问题": 133,
"验证失败": 673
},
"failureCount": 2167,
"failureRate": 0.9273,
"failureCount": 2169,
"failureRate": 0.9269,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 11,
"successCount": 170,
"successRate": 0.0727,
"total": 2337,
"successCount": 171,
"successRate": 0.0731,
"total": 2340,
"unresolvedFailureCount": 1394
},
"warnings": [
"GPU Biren_166m 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 Ascend_910-b3 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。",
@@ -15749,7 +15775,7 @@
"GPU Sunrise_pt-200-x1 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 MetaX_c-500 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 Biren_166m 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 Ascend_910-b4|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。",
"组合 Iluvatar_mrv-100|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -15774,6 +15800,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2440,
"summarizedRecords": 2443,
"version": 1
}