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

state: generation 9715 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-19 08:31:56 +00:00
parent 8e73351226
commit 86bafa0ad6
9 changed files with 1943 additions and 1895 deletions
Download Patch File Download Diff File Expand all files Collapse all files

204
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-19T08:18:41.708825+00:00",
"lastSyncTime": "2026-09-19T08:18:41.447306+00:00",
"generatedAt": "2026-09-19T08:29:40.876758+00:00",
"lastSyncTime": "2026-09-19T08:29:40.588066+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1922,15 +1922,15 @@
"unresolvedFailureCount": 188
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 6,
"attributableFailureCount": 7,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 6
"framework_architecture_unsupported": 7
},
"failureCount": 18,
"failureCount": 19,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
@@ -1940,7 +1940,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 18,
"total": 19,
"unresolvedFailureCount": 12
},
"Ascend_910-b4|vllm|text-generation": {
@@ -1998,26 +1998,26 @@
"unresolvedFailureCount": 60
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 28,
"decisionFailureRate": 0.7368,
"decisionSuccessRate": 0.2632,
"decisionTotal": 38,
"attributableFailureCount": 29,
"decisionFailureRate": 0.7436,
"decisionSuccessRate": 0.2564,
"decisionTotal": 39,
"failureBreakdown": {
"framework_architecture_unsupported": 22,
"model_load": 5,
"model_load": 6,
"tokenizer_compatibility": 1
},
"failureCount": 28,
"failureRate": 0.7368,
"failureCount": 29,
"failureRate": 0.7436,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 10,
"successRate": 0.2632,
"successRate": 0.2564,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 38,
"total": 39,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -2862,30 +2862,30 @@
"unresolvedFailureCount": 910
},
"vllm": {
"attributableFailureCount": 422,
"decisionFailureRate": 0.8847,
"decisionSuccessRate": 0.1153,
"decisionTotal": 477,
"attributableFailureCount": 423,
"decisionFailureRate": 0.8849,
"decisionSuccessRate": 0.1151,
"decisionTotal": 478,
"failureBreakdown": {
"ambiguous_runtime": 246,
"backend_operator": 40,
"framework_architecture_unsupported": 317,
"memory_capacity": 7,
"model_load": 32,
"model_load": 33,
"platform_infrastructure": 2,
"repository_structure": 8,
"runtime_memory": 6,
"tokenizer_compatibility": 12,
"参数/模板问题": 40
},
"failureCount": 710,
"failureRate": 0.9281,
"failureCount": 711,
"failureRate": 0.9282,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 55,
"successRate": 0.0719,
"total": 765,
"successRate": 0.0718,
"total": 766,
"unresolvedFailureCount": 286
},
"vllm-mlu": {
@@ -2979,26 +2979,26 @@
"unresolvedFailureCount": 88
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 18,
"decisionFailureRate": 0.9474,
"decisionSuccessRate": 0.0526,
"decisionTotal": 19,
"attributableFailureCount": 19,
"decisionFailureRate": 0.95,
"decisionSuccessRate": 0.05,
"decisionTotal": 20,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 18
"framework_architecture_unsupported": 19
},
"failureCount": 36,
"failureRate": 0.973,
"failureCount": 37,
"failureRate": 0.9737,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.027,
"total": 37,
"successRate": 0.0263,
"total": 38,
"unresolvedFailureCount": 18
}
},
"generatedAt": "2026-09-19T08:18:41.703239+00:00",
"generatedAt": "2026-09-19T08:29:40.871173+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 62,
@@ -3024,13 +3024,13 @@
"unresolvedFailureCount": 76
},
"Ascend_910-b4": {
"attributableFailureCount": 65,
"decisionFailureRate": 0.9701,
"decisionSuccessRate": 0.0299,
"decisionTotal": 67,
"attributableFailureCount": 66,
"decisionFailureRate": 0.9706,
"decisionSuccessRate": 0.0294,
"decisionTotal": 68,
"failureBreakdown": {
"ambiguous_runtime": 55,
"framework_architecture_unsupported": 60,
"framework_architecture_unsupported": 61,
"memory_capacity": 1,
"model_load": 1,
"repository_structure": 1,
@@ -3038,40 +3038,40 @@
"参数/模板问题": 13,
"验证失败": 175
},
"failureCount": 308,
"failureRate": 0.9935,
"failureCount": 309,
"failureRate": 0.9936,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0065,
"total": 310,
"successRate": 0.0064,
"total": 311,
"unresolvedFailureCount": 243
},
"Biren_166m": {
"attributableFailureCount": 68,
"decisionFailureRate": 0.85,
"decisionSuccessRate": 0.15,
"decisionTotal": 80,
"attributableFailureCount": 69,
"decisionFailureRate": 0.8519,
"decisionSuccessRate": 0.1481,
"decisionTotal": 81,
"failureBreakdown": {
"ambiguous_runtime": 32,
"backend_operator": 4,
"framework_architecture_unsupported": 51,
"memory_capacity": 1,
"model_load": 8,
"model_load": 9,
"runtime_memory": 2,
"tokenizer_compatibility": 2,
"参数/模板问题": 1,
"验证失败": 27
},
"failureCount": 128,
"failureRate": 0.9143,
"failureCount": 129,
"failureRate": 0.9149,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 12,
"successRate": 0.0857,
"total": 140,
"successRate": 0.0851,
"total": 141,
"unresolvedFailureCount": 60
},
"Cambricon_mlu-370-x4": {
@@ -3791,14 +3791,14 @@
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|none": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "qwen3_5",
@@ -3810,7 +3810,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3|none": {
@@ -3883,14 +3883,14 @@
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|llama|awq": {
"attributableFailureCount": 4,
"attributableFailureCount": 5,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"decisionTotal": 5,
"failureBreakdown": {
"model_load": 4
"model_load": 5
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "llama",
@@ -3902,7 +3902,7 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 4,
"total": 5,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|llama|none": {
@@ -9222,6 +9222,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -9294,6 +9318,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|llama|awq|30": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 30,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|llama|awq|32": {
"attributableFailureCount": 4,
"decisionFailureRate": 1.0,
@@ -15357,19 +15405,19 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2310,
"totalRecords": 2413,
"terminalRecords": 2312,
"totalRecords": 2415,
"totals": {
"attributableFailureCount": 755,
"decisionFailureRate": 0.8279,
"decisionSuccessRate": 0.1721,
"decisionTotal": 912,
"attributableFailureCount": 757,
"decisionFailureRate": 0.8282,
"decisionSuccessRate": 0.1718,
"decisionTotal": 914,
"failureBreakdown": {
"ambiguous_runtime": 581,
"backend_operator": 55,
"framework_architecture_unsupported": 506,
"framework_architecture_unsupported": 507,
"memory_capacity": 12,
"model_load": 88,
"model_load": 89,
"platform_infrastructure": 11,
"repository_structure": 8,
"runtime_memory": 20,
@@ -15377,18 +15425,18 @@
"参数/模板问题": 133,
"验证失败": 673
},
"failureCount": 2153,
"failureRate": 0.932,
"failureCount": 2155,
"failureRate": 0.9321,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 11,
"successCount": 157,
"successRate": 0.068,
"total": 2310,
"successRate": 0.0679,
"total": 2312,
"unresolvedFailureCount": 1387
},
"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。",
@@ -15399,7 +15447,7 @@
"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。",
@@ -15424,6 +15472,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2413,
"summarizedRecords": 2415,
"version": 1
}