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

state: generation 4955 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 04:47:26 +00:00
parent 37026ce883
commit 17208b0206
11 changed files with 2077 additions and 2032 deletions
Download Patch File Download Diff File Expand all files Collapse all files

163
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T04:27:59.073636+00:00",
"lastSyncTime": "2026-09-10T04:27:58.701482+00:00",
"generatedAt": "2026-09-10T04:45:49.713641+00:00",
"lastSyncTime": "2026-09-10T04:45:49.293213+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1762,22 +1762,22 @@
"decisionSuccessRate": 0.2,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 2,
"ambiguous_runtime": 3,
"backend_operator": 3,
"framework_architecture_unsupported": 1
},
"failureCount": 6,
"failureRate": 0.8571,
"failureCount": 7,
"failureRate": 0.875,
"framework": "vllm_0_17_0_corex_4_4_0",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.1429,
"successRate": 0.125,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 7,
"unresolvedFailureCount": 2
"total": 8,
"unresolvedFailureCount": 3
},
"Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 14,
@@ -2243,14 +2243,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 35,
"failureBreakdown": {
"ambiguous_runtime": 8,
"ambiguous_runtime": 9,
"framework_architecture_unsupported": 27,
"memory_capacity": 1,
"model_load": 3,
"repository_structure": 3,
"runtime_memory": 1
},
"failureCount": 43,
"failureCount": 44,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2260,8 +2260,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 43,
"unresolvedFailureCount": 8
"total": 44,
"unresolvedFailureCount": 9
}
},
"frameworkSummaries": {
@@ -2333,7 +2333,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 230,
"failureBreakdown": {
"ambiguous_runtime": 134,
"ambiguous_runtime": 135,
"backend_operator": 24,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2344,15 +2344,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 386,
"failureCount": 387,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"total": 386,
"unresolvedFailureCount": 155
"total": 387,
"unresolvedFailureCount": 156
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2399,19 +2399,19 @@
"decisionSuccessRate": 0.2,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 2,
"ambiguous_runtime": 3,
"backend_operator": 3,
"framework_architecture_unsupported": 1
},
"failureCount": 6,
"failureRate": 0.8571,
"failureCount": 7,
"failureRate": 0.875,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.1429,
"total": 7,
"unresolvedFailureCount": 2
"successRate": 0.125,
"total": 8,
"unresolvedFailureCount": 3
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 32,
@@ -2455,7 +2455,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T04:27:59.069416+00:00",
"generatedAt": "2026-09-10T04:45:49.709300+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2599,7 +2599,7 @@
"decisionSuccessRate": 0.24,
"decisionTotal": 25,
"failureBreakdown": {
"ambiguous_runtime": 10,
"ambiguous_runtime": 11,
"backend_operator": 5,
"framework_architecture_unsupported": 8,
"model_load": 4,
@@ -2607,15 +2607,15 @@
"参数/模板问题": 1,
"验证失败": 30
},
"failureCount": 60,
"failureRate": 0.9091,
"failureCount": 61,
"failureRate": 0.9104,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 6,
"successRate": 0.0909,
"total": 66,
"unresolvedFailureCount": 41
"successRate": 0.0896,
"total": 67,
"unresolvedFailureCount": 42
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 68,
@@ -2762,7 +2762,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 38,
"failureBreakdown": {
"ambiguous_runtime": 10,
"ambiguous_runtime": 11,
"framework_architecture_unsupported": 30,
"memory_capacity": 1,
"model_load": 3,
@@ -2771,15 +2771,15 @@
"参数/模板问题": 8,
"验证失败": 27
},
"failureCount": 83,
"failureCount": 84,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 83,
"unresolvedFailureCount": 45
"total": 84,
"unresolvedFailureCount": 46
}
},
"observedGpuMemoryGiB": {
@@ -3212,6 +3212,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "starcoder2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|aquila3|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -4083,19 +4106,19 @@
"unresolvedFailureCount": 4
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 4,
"attributableFailureCount": 3,
"consecutiveFailures": 2,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.6667,
"decisionSuccessRate": 0.3333,
"decisionTotal": 6,
"decisionFailureRate": 0.6,
"decisionSuccessRate": 0.4,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 10,
"framework_architecture_unsupported": 3,
"framework_architecture_unsupported": 2,
"tokenizer_compatibility": 1
},
"failureCount": 14,
"failureRate": 0.875,
"failureCount": 13,
"failureRate": 0.8667,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T01:59:31.241099+00:00",
@@ -4103,10 +4126,10 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.125,
"successRate": 0.1333,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 16,
"total": 15,
"unresolvedFailureCount": 10
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
@@ -4655,16 +4678,16 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 10,
"failureBreakdown": {
"ambiguous_runtime": 6,
"ambiguous_runtime": 7,
"framework_architecture_unsupported": 8,
"model_load": 1,
"repository_structure": 1
},
"failureCount": 16,
"failureCount": 17,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T02:50:12.317776+00:00",
"lastTerminalAt": "2026-09-10T04:45:49.293187+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4672,8 +4695,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 16,
"unresolvedFailureCount": 6
"total": 17,
"unresolvedFailureCount": 7
}
},
"recentProfileCombinationStats": {
@@ -5801,6 +5824,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|starcoder2|compressed-tensors|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 34,
"modelType": "starcoder2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|aquila3|none|12": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -6858,15 +6905,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1500,
"totalRecords": 1587,
"terminalRecords": 1502,
"totalRecords": 1589,
"totals": {
"attributableFailureCount": 399,
"decisionFailureRate": 0.8906,
"decisionSuccessRate": 0.1094,
"decisionTotal": 448,
"failureBreakdown": {
"ambiguous_runtime": 282,
"ambiguous_runtime": 284,
"backend_operator": 29,
"framework_architecture_unsupported": 270,
"memory_capacity": 11,
@@ -6878,21 +6925,21 @@
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1451,
"failureRate": 0.9673,
"failureCount": 1453,
"failureRate": 0.9674,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 49,
"successRate": 0.0327,
"total": 1500,
"unresolvedFailureCount": 1050
"successRate": 0.0326,
"total": 1502,
"unresolvedFailureCount": 1052
},
"warnings": [
"GPU Cambricon_mlu-370-x8 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 Iluvatar_mrv-100 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。",
"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。",
@@ -6900,7 +6947,7 @@
"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 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 Iluvatar_bi-150 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-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 Biren_166m|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -6921,6 +6968,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1587,
"summarizedRecords": 1589,
"version": 1
}