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

state: generation 21835 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-07 13:22:42 +00:00
parent ddb84d93ad
commit 6720f307b5
9 changed files with 2170 additions and 2098 deletions
Download Patch File Download Diff File Expand all files Collapse all files

151
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-07T13:06:44.988876+00:00",
"lastSyncTime": "2026-10-07T13:06:44.750866+00:00",
"generatedAt": "2026-10-07T13:20:53.520866+00:00",
"lastSyncTime": "2026-10-07T13:20:53.257507+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -5324,19 +5324,19 @@
"unresolvedFailureCount": 72
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
"attributableFailureCount": 64,
"attributableFailureCount": 65,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 64,
"decisionTotal": 65,
"failureBreakdown": {
"ambiguous_runtime": 48,
"framework_architecture_unsupported": 26,
"model_load": 14,
"model_load": 15,
"repository_structure": 5,
"runtime_memory": 19,
"参数/模板问题": 24
},
"failureCount": 136,
"failureCount": 137,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"pendingCount": 0,
@@ -5346,7 +5346,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 136,
"total": 137,
"unresolvedFailureCount": 72
},
"hygon_k100-ai|vllm|text-generation": {
@@ -5580,26 +5580,26 @@
"unresolvedFailureCount": 109
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 64,
"attributableFailureCount": 65,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 64,
"decisionTotal": 65,
"failureBreakdown": {
"ambiguous_runtime": 48,
"framework_architecture_unsupported": 26,
"model_load": 14,
"model_load": 15,
"repository_structure": 5,
"runtime_memory": 19,
"参数/模板问题": 24
},
"failureCount": 136,
"failureCount": 137,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 136,
"total": 137,
"unresolvedFailureCount": 72
},
"vllm_0_17_0_corex_4_4_0": {
@@ -5680,7 +5680,7 @@
"unresolvedFailureCount": 237
}
},
"generatedAt": "2026-10-07T13:06:44.968997+00:00",
"generatedAt": "2026-10-07T13:20:53.504133+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 119,
@@ -6073,10 +6073,10 @@
"unresolvedFailureCount": 1322
},
"hygon_k100-ai": {
"attributableFailureCount": 744,
"decisionFailureRate": 0.9538,
"decisionSuccessRate": 0.0462,
"decisionTotal": 780,
"attributableFailureCount": 745,
"decisionFailureRate": 0.9539,
"decisionSuccessRate": 0.0461,
"decisionTotal": 781,
"failureBreakdown": {
"ambiguous_runtime": 346,
"architecture_compatibility": 32,
@@ -6084,7 +6084,7 @@
"context_length": 46,
"framework_architecture_unsupported": 258,
"memory_capacity": 59,
"model_load": 74,
"model_load": 75,
"platform_infrastructure": 4,
"repository_structure": 121,
"runtime_memory": 74,
@@ -6093,14 +6093,14 @@
"日志缺失": 66,
"验证失败": 27
},
"failureCount": 1592,
"failureCount": 1593,
"failureRate": 0.9779,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 36,
"successRate": 0.0221,
"total": 1628,
"total": 1629,
"unresolvedFailureCount": 844
}
},
@@ -23993,6 +23993,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|gpt_oss|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"modelType": "gpt_oss",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|hrm_text|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -25401,9 +25424,9 @@
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1,
"参数/模板问题": 7
"参数/模板问题": 6
},
"failureCount": 8,
"failureCount": 7,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
@@ -25415,8 +25438,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 8,
"unresolvedFailureCount": 8
"total": 7,
"unresolvedFailureCount": 7
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation": {
"attributableFailureCount": 1,
@@ -25915,15 +25938,16 @@
"unresolvedFailureCount": 1
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 3,
"ambiguous_runtime": 2,
"framework_architecture_unsupported": 2,
"model_load": 1,
"repository_structure": 1,
"runtime_memory": 1,
"参数/模板问题": 13
@@ -25941,7 +25965,7 @@
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 16
"unresolvedFailureCount": 15
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 4,
@@ -29071,6 +29095,31 @@
"total": 1,
"unresolvedFailureCount": 1
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|gpt_oss|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"lastTerminalAt": "2026-10-07T13:20:53.257507+00:00",
"modelType": "gpt_oss",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"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|compressed-tensors": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
@@ -56456,6 +56505,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|gpt_oss|none|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"loadSizeLog2Bucket": 33,
"modelType": "gpt_oss",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|hrm_text|none|31": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -58213,13 +58286,13 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17380,
"totalRecords": 17637,
"terminalRecords": 17381,
"totalRecords": 17638,
"totals": {
"attributableFailureCount": 6246,
"attributableFailureCount": 6247,
"decisionFailureRate": 0.8646,
"decisionSuccessRate": 0.1354,
"decisionTotal": 7224,
"decisionTotal": 7225,
"failureBreakdown": {
"ambiguous_runtime": 4563,
"architecture_compatibility": 212,
@@ -58228,7 +58301,7 @@
"context_length": 327,
"framework_architecture_unsupported": 2268,
"memory_capacity": 1206,
"model_load": 569,
"model_load": 570,
"platform_infrastructure": 952,
"repository_structure": 742,
"runtime_memory": 101,
@@ -58237,14 +58310,14 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16402,
"failureCount": 16403,
"failureRate": 0.9437,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 952,
"successCount": 978,
"successRate": 0.0563,
"total": 17380,
"total": 17381,
"unresolvedFailureCount": 9204
},
"warnings": [
@@ -58254,14 +58327,14 @@
"GPU hygon_k100-ai 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 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 Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Kunlunxin_p-800 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 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 Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-100 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 Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
"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 Ascend_910-b3|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_mrv-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -58306,6 +58379,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17637,
"summarizedRecords": 17638,
"version": 1
}