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

state: generation 6518 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-13 04:33:06 +00:00
parent 9891296111
commit 30faa784b4
9 changed files with 2326 additions and 2277 deletions
Download Patch File Download Diff File Expand all files Collapse all files

113
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-13T04:23:07.879464+00:00",
"lastSyncTime": "2026-09-13T04:23:07.613289+00:00",
"generatedAt": "2026-09-13T04:31:31.956372+00:00",
"lastSyncTime": "2026-09-13T04:31:31.632761+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2214,18 +2214,18 @@
"unresolvedFailureCount": 34
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 45,
"attributableFailureCount": 46,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 45,
"decisionTotal": 46,
"failureBreakdown": {
"backend_operator": 1,
"backend_operator": 2,
"framework_architecture_unsupported": 4,
"platform_infrastructure": 2,
"tokenizer_compatibility": 40,
"参数/模板问题": 6
},
"failureCount": 53,
"failureCount": 54,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -2235,7 +2235,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 53,
"total": 54,
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -2575,27 +2575,27 @@
"unresolvedFailureCount": 4
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 48,
"attributableFailureCount": 49,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 48,
"decisionTotal": 49,
"failureBreakdown": {
"ambiguous_runtime": 37,
"backend_operator": 1,
"backend_operator": 2,
"framework_architecture_unsupported": 6,
"model_load": 1,
"platform_infrastructure": 2,
"tokenizer_compatibility": 40,
"参数/模板问题": 7
},
"failureCount": 94,
"failureCount": 95,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 0,
"successRate": 0.0,
"total": 94,
"total": 95,
"unresolvedFailureCount": 44
},
"vllm_tokenizer_patch": {
@@ -2617,7 +2617,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-13T04:23:07.875222+00:00",
"generatedAt": "2026-09-13T04:31:31.950508+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 31,
@@ -2877,27 +2877,27 @@
"unresolvedFailureCount": 77
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 49,
"decisionFailureRate": 0.98,
"decisionSuccessRate": 0.02,
"decisionTotal": 50,
"attributableFailureCount": 50,
"decisionFailureRate": 0.9804,
"decisionSuccessRate": 0.0196,
"decisionTotal": 51,
"failureBreakdown": {
"ambiguous_runtime": 1,
"backend_operator": 1,
"backend_operator": 2,
"framework_architecture_unsupported": 5,
"platform_infrastructure": 3,
"tokenizer_compatibility": 43,
"参数/模板问题": 10,
"验证失败": 32
},
"failureCount": 95,
"failureRate": 0.9896,
"failureCount": 96,
"failureRate": 0.9897,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 1,
"successRate": 0.0104,
"total": 96,
"successRate": 0.0103,
"total": 97,
"unresolvedFailureCount": 43
},
"Vastai_va16": {
@@ -4182,6 +4182,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|awq": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"backend_operator": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -7079,6 +7102,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|awq|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"backend_operator": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 33,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|31": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -7368,16 +7415,16 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1762,
"totalRecords": 1849,
"terminalRecords": 1763,
"totalRecords": 1850,
"totals": {
"attributableFailureCount": 509,
"decisionFailureRate": 0.8961,
"decisionSuccessRate": 0.1039,
"decisionTotal": 568,
"attributableFailureCount": 510,
"decisionFailureRate": 0.8963,
"decisionSuccessRate": 0.1037,
"decisionTotal": 569,
"failureBreakdown": {
"ambiguous_runtime": 414,
"backend_operator": 42,
"backend_operator": 43,
"framework_architecture_unsupported": 320,
"memory_capacity": 11,
"model_load": 73,
@@ -7388,20 +7435,21 @@
"参数/模板问题": 103,
"验证失败": 673
},
"failureCount": 1703,
"failureCount": 1704,
"failureRate": 0.9665,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 59,
"successRate": 0.0335,
"total": 1762,
"total": 1763,
"unresolvedFailureCount": 1190
},
"warnings": [
"GPU Ascend_910-b3 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 Mthreads_s4000 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 hygon_k100-ai 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_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -7410,7 +7458,6 @@
"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-150 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。",
"组合 hygon_k100-ai|vllm-patch-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 hygon_k100-ai|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|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -7433,6 +7480,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1849,
"summarizedRecords": 1850,
"version": 1
}