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

state: generation 5311 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 18:41:05 +00:00
parent e085fe5ff4
commit f8e2eca061
9 changed files with 2230 additions and 2251 deletions
Download Patch File Download Diff File Expand all files Collapse all files

115
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T17:40:38.619379+00:00",
"lastSyncTime": "2026-09-10T17:40:38.407692+00:00",
"generatedAt": "2026-09-10T18:38:45.442913+00:00",
"lastSyncTime": "2026-09-10T18:38:45.206121+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1800,20 +1800,21 @@
"framework_architecture_unsupported": 47,
"memory_capacity": 1,
"model_load": 24,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 138,
"failureRate": 0.9324,
"failureCount": 139,
"failureRate": 0.9329,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0676,
"successRate": 0.0671,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 148,
"total": 149,
"unresolvedFailureCount": 66
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -2301,18 +2302,19 @@
"framework_architecture_unsupported": 88,
"memory_capacity": 5,
"model_load": 26,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3,
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 978,
"failureRate": 0.9532,
"failureCount": 979,
"failureRate": 0.9533,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"platformFailureCount": 1,
"successCount": 48,
"successRate": 0.0468,
"total": 1026,
"successRate": 0.0467,
"total": 1027,
"unresolvedFailureCount": 852
},
"vllm": {
@@ -2443,7 +2445,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T17:40:38.613684+00:00",
"generatedAt": "2026-09-10T18:38:45.436829+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2615,17 +2617,18 @@
"framework_architecture_unsupported": 47,
"memory_capacity": 1,
"model_load": 24,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 138,
"failureRate": 0.9324,
"failureCount": 139,
"failureRate": 0.9329,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0676,
"total": 148,
"successRate": 0.0671,
"total": 149,
"unresolvedFailureCount": 66
},
"Kunlunxin_p-800": {
@@ -4169,11 +4172,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 14,
"ambiguous_runtime": 13,
"framework_architecture_unsupported": 4,
"参数/模板问题": 1
},
"failureCount": 19,
"failureCount": 18,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastPlatformFailureAt": null,
@@ -4185,8 +4188,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 19,
"unresolvedFailureCount": 15
"total": 18,
"unresolvedFailureCount": 14
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 3,
@@ -4267,25 +4270,26 @@
"unresolvedFailureCount": 3
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 16,
"attributableFailureCount": 15,
"consecutiveFailures": 5,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8421,
"decisionSuccessRate": 0.1579,
"decisionTotal": 19,
"consecutivePlatformFailures": 1,
"decisionFailureRate": 0.8333,
"decisionSuccessRate": 0.1667,
"decisionTotal": 18,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 9,
"model_load": 7
"model_load": 6,
"platform_infrastructure": 1
},
"failureCount": 17,
"failureRate": 0.85,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T12:40:42.405633+00:00",
"lastPlatformFailureAt": "2026-09-10T18:33:21+00:00",
"lastTerminalAt": "2026-09-10T18:38:45.206121+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.15,
"targetGpu": "Iluvatar_mrv-100",
@@ -4630,31 +4634,6 @@
"total": 4,
"unresolvedFailureCount": 4
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastTerminalAt": "2026-09-08T15:41:33.599000+00:00",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|nemotron_h|modelopt": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -7169,8 +7148,8 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1615,
"totalRecords": 1702,
"terminalRecords": 1616,
"totalRecords": 1703,
"totals": {
"attributableFailureCount": 421,
"decisionFailureRate": 0.8901,
@@ -7182,37 +7161,38 @@
"framework_architecture_unsupported": 272,
"memory_capacity": 11,
"model_load": 48,
"platform_infrastructure": 3,
"platform_infrastructure": 4,
"repository_structure": 5,
"runtime_memory": 6,
"tokenizer_compatibility": 39,
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1563,
"failureCount": 1564,
"failureRate": 0.9678,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"platformFailureCount": 4,
"successCount": 52,
"successRate": 0.0322,
"total": 1615,
"total": 1616,
"unresolvedFailureCount": 1139
},
"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。",
@@ -7227,11 +7207,10 @@
"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": 1702,
"summarizedRecords": 1703,
"version": 1
}