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

state: generation 5364 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 21:26:25 +00:00
parent d551d1fdfb
commit 3ad38d905b
9 changed files with 2045 additions and 2072 deletions
Download Patch File Download Diff File Expand all files Collapse all files

129
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T20:06:20.200156+00:00",
"lastSyncTime": "2026-09-10T20:06:18.925896+00:00",
"generatedAt": "2026-09-10T21:23:30.812981+00:00",
"lastSyncTime": "2026-09-10T21:23:30.606628+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1999,7 +1999,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 32,
"failureBreakdown": {
"ambiguous_runtime": 34,
"ambiguous_runtime": 36,
"backend_operator": 4,
"framework_architecture_unsupported": 22,
"memory_capacity": 1,
@@ -2008,7 +2008,7 @@
"runtime_memory": 2,
"参数/模板问题": 3
},
"failureCount": 69,
"failureCount": 71,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2018,8 +2018,8 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 69,
"unresolvedFailureCount": 37
"total": 71,
"unresolvedFailureCount": 39
},
"Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2321,7 +2321,7 @@
"decisionSuccessRate": 0.0083,
"decisionTotal": 242,
"failureBreakdown": {
"ambiguous_runtime": 186,
"ambiguous_runtime": 188,
"backend_operator": 33,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2332,15 +2332,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 24
},
"failureCount": 451,
"failureCount": 453,
"failureRate": 0.9956,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 2,
"successRate": 0.0044,
"total": 453,
"unresolvedFailureCount": 210
"total": 455,
"unresolvedFailureCount": 212
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2443,7 +2443,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T20:06:20.193221+00:00",
"generatedAt": "2026-09-10T21:23:30.808052+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2680,7 +2680,7 @@
"decisionSuccessRate": 0.0571,
"decisionTotal": 35,
"failureBreakdown": {
"ambiguous_runtime": 34,
"ambiguous_runtime": 36,
"backend_operator": 4,
"framework_architecture_unsupported": 22,
"memory_capacity": 1,
@@ -2690,15 +2690,15 @@
"参数/模板问题": 10,
"验证失败": 26
},
"failureCount": 103,
"failureRate": 0.981,
"failureCount": 105,
"failureRate": 0.9813,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.019,
"total": 105,
"unresolvedFailureCount": 70
"successRate": 0.0187,
"total": 107,
"unresolvedFailureCount": 72
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 36,
@@ -4163,17 +4163,16 @@
"unresolvedFailureCount": 14
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2,
"framework_architecture_unsupported": 1
"ambiguous_runtime": 1
},
"failureCount": 3,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastPlatformFailureAt": null,
@@ -4185,8 +4184,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 2
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 3,
@@ -4396,23 +4395,22 @@
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 14,
"ambiguous_runtime": 16,
"backend_operator": 3,
"framework_architecture_unsupported": 1,
"runtime_memory": 1
"framework_architecture_unsupported": 1
},
"failureCount": 19,
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T19:08:02.004199+00:00",
"lastTerminalAt": "2026-09-10T21:23:30.606595+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4420,8 +4418,8 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 19,
"unresolvedFailureCount": 14
"total": 20,
"unresolvedFailureCount": 16
},
"Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -4613,9 +4611,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 1
},
"failureCount": 2,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastTerminalAt": "2026-09-10T13:06:08.293453+00:00",
@@ -4628,33 +4626,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|nemotron_h|modelopt": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastTerminalAt": "2026-09-08T20:33:46.399743+00:00",
"modelType": "nemotron_h",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm|text-generation|qwen3_5_moe|eschamoe": {
"attributableFailureCount": 1,
@@ -6995,15 +6968,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1631,
"totalRecords": 1718,
"terminalRecords": 1633,
"totalRecords": 1720,
"totals": {
"attributableFailureCount": 426,
"decisionFailureRate": 0.8912,
"decisionSuccessRate": 0.1088,
"decisionTotal": 478,
"failureBreakdown": {
"ambiguous_runtime": 378,
"ambiguous_runtime": 380,
"backend_operator": 40,
"framework_architecture_unsupported": 273,
"memory_capacity": 11,
@@ -7015,31 +6988,30 @@
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1579,
"failureRate": 0.9681,
"failureCount": 1581,
"failureRate": 0.9682,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 52,
"successRate": 0.0319,
"total": 1631,
"unresolvedFailureCount": 1149
"successRate": 0.0318,
"total": 1633,
"unresolvedFailureCount": 1151
},
"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 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。",
"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 Cambricon_mlu-370-x4 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。",
@@ -7054,10 +7026,11 @@
"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": 1718,
"summarizedRecords": 1720,
"version": 1
}