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

state: generation 5245 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 15:58:19 +00:00
parent 0c70d968ab
commit 09c97719fc
9 changed files with 2217 additions and 2219 deletions
Download Patch File Download Diff File Expand all files Collapse all files

114
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T15:48:18.040272+00:00",
"lastSyncTime": "2026-09-10T15:48:17.745945+00:00",
"generatedAt": "2026-09-10T15:56:47.793655+00:00",
"lastSyncTime": "2026-09-10T15:56:47.546297+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1905,29 +1905,29 @@
"unresolvedFailureCount": 56
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 45,
"decisionFailureRate": 0.9574,
"decisionSuccessRate": 0.0426,
"decisionTotal": 47,
"attributableFailureCount": 46,
"decisionFailureRate": 0.9583,
"decisionSuccessRate": 0.0417,
"decisionTotal": 48,
"failureBreakdown": {
"ambiguous_runtime": 7,
"backend_operator": 26,
"backend_operator": 27,
"framework_architecture_unsupported": 14,
"memory_capacity": 1,
"model_load": 4,
"参数/模板问题": 9
},
"failureCount": 61,
"failureRate": 0.9683,
"failureCount": 62,
"failureRate": 0.9688,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0317,
"successRate": 0.0312,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 63,
"total": 64,
"unresolvedFailureCount": 16
},
"Mthreads_s4000|llamacpp|text-generation": {
@@ -2316,13 +2316,13 @@
"unresolvedFailureCount": 846
},
"vllm": {
"attributableFailureCount": 239,
"attributableFailureCount": 240,
"decisionFailureRate": 0.9917,
"decisionSuccessRate": 0.0083,
"decisionTotal": 241,
"decisionTotal": 242,
"failureBreakdown": {
"ambiguous_runtime": 174,
"backend_operator": 32,
"backend_operator": 33,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
"model_load": 18,
@@ -2332,14 +2332,14 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 24
},
"failureCount": 438,
"failureCount": 439,
"failureRate": 0.9955,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 2,
"successRate": 0.0045,
"total": 440,
"total": 441,
"unresolvedFailureCount": 198
},
"vllm-mlu": {
@@ -2443,7 +2443,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T15:48:18.035267+00:00",
"generatedAt": "2026-09-10T15:56:47.789236+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2650,27 +2650,27 @@
"unresolvedFailureCount": 89
},
"MetaX_c-500": {
"attributableFailureCount": 45,
"decisionFailureRate": 0.8036,
"decisionSuccessRate": 0.1964,
"decisionTotal": 56,
"attributableFailureCount": 46,
"decisionFailureRate": 0.807,
"decisionSuccessRate": 0.193,
"decisionTotal": 57,
"failureBreakdown": {
"ambiguous_runtime": 7,
"backend_operator": 26,
"backend_operator": 27,
"framework_architecture_unsupported": 14,
"memory_capacity": 1,
"model_load": 4,
"参数/模板问题": 17,
"验证失败": 48
},
"failureCount": 117,
"failureRate": 0.9141,
"failureCount": 118,
"failureRate": 0.9147,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 11,
"successRate": 0.0859,
"total": 128,
"successRate": 0.0853,
"total": 129,
"unresolvedFailureCount": 72
},
"Mthreads_s4000": {
@@ -3568,15 +3568,15 @@
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 13,
"decisionFailureRate": 0.9286,
"decisionSuccessRate": 0.0714,
"decisionTotal": 14,
"attributableFailureCount": 14,
"decisionFailureRate": 0.9333,
"decisionSuccessRate": 0.0667,
"decisionTotal": 15,
"failureBreakdown": {
"backend_operator": 13
"backend_operator": 14
},
"failureCount": 13,
"failureRate": 0.9286,
"failureCount": 14,
"failureRate": 0.9333,
"framework": "vllm",
"modelType": "llama",
"pendingCount": 0,
@@ -3584,10 +3584,10 @@
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 1,
"successRate": 0.0714,
"successRate": 0.0667,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 14,
"total": 15,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|phi3small|compressed-tensors": {
@@ -6545,14 +6545,14 @@
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors|33": {
"attributableFailureCount": 6,
"attributableFailureCount": 7,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"decisionTotal": 7,
"failureBreakdown": {
"backend_operator": 6
"backend_operator": 7
},
"failureCount": 6,
"failureCount": 7,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
@@ -6565,7 +6565,7 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 6,
"total": 7,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|phi3small|compressed-tensors|33": {
@@ -7121,16 +7121,16 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1602,
"totalRecords": 1689,
"terminalRecords": 1603,
"totalRecords": 1690,
"totals": {
"attributableFailureCount": 419,
"decisionFailureRate": 0.8896,
"decisionSuccessRate": 0.1104,
"decisionTotal": 471,
"attributableFailureCount": 420,
"decisionFailureRate": 0.8898,
"decisionSuccessRate": 0.1102,
"decisionTotal": 472,
"failureBreakdown": {
"ambiguous_runtime": 357,
"backend_operator": 39,
"backend_operator": 40,
"framework_architecture_unsupported": 272,
"memory_capacity": 11,
"model_load": 48,
@@ -7141,30 +7141,31 @@
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1550,
"failureRate": 0.9675,
"failureCount": 1551,
"failureRate": 0.9676,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 52,
"successRate": 0.0325,
"total": 1602,
"successRate": 0.0324,
"total": 1603,
"unresolvedFailureCount": 1128
},
"warnings": [
"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 Iluvatar_mrv-100 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 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。",
"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 Iluvatar_bi-150 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 Cambricon_mlu-370-x8 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 Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
"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。",
"组合 Cambricon_mlu-370-x4|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 Mthreads_s4000|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 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -7179,11 +7180,10 @@
"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 Iluvatar_bi-150|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 Vastai_va16|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-x4|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 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。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1689,
"summarizedRecords": 1690,
"version": 1
}