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

state: generation 5075 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 08:30:11 +00:00
parent efa8c29eb9
commit d81fb93c58
10 changed files with 2384 additions and 2385 deletions
Download Patch File Download Diff File Expand all files Collapse all files

154
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T08:19:33.977040+00:00",
"lastSyncTime": "2026-09-10T08:19:33.742658+00:00",
"generatedAt": "2026-09-10T08:28:01.488214+00:00",
"lastSyncTime": "2026-09-10T08:28:01.218249+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1911,29 +1911,29 @@
"unresolvedFailureCount": 56
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 40,
"decisionFailureRate": 0.9756,
"decisionSuccessRate": 0.0244,
"decisionTotal": 41,
"attributableFailureCount": 41,
"decisionFailureRate": 0.9762,
"decisionSuccessRate": 0.0238,
"decisionTotal": 42,
"failureBreakdown": {
"ambiguous_runtime": 7,
"backend_operator": 21,
"backend_operator": 22,
"framework_architecture_unsupported": 14,
"memory_capacity": 1,
"model_load": 4,
"参数/模板问题": 9
},
"failureCount": 56,
"failureRate": 0.9825,
"failureCount": 57,
"failureRate": 0.9828,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0175,
"successRate": 0.0172,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 57,
"total": 58,
"unresolvedFailureCount": 16
},
"Mthreads_s4000|llamacpp|text-generation": {
@@ -2006,7 +2006,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 30,
"failureBreakdown": {
"ambiguous_runtime": 23,
"ambiguous_runtime": 24,
"backend_operator": 2,
"framework_architecture_unsupported": 22,
"memory_capacity": 1,
@@ -2014,7 +2014,7 @@
"repository_structure": 1,
"runtime_memory": 2
},
"failureCount": 53,
"failureCount": 54,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2024,8 +2024,8 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 53,
"unresolvedFailureCount": 23
"total": 54,
"unresolvedFailureCount": 24
},
"Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2320,13 +2320,13 @@
"unresolvedFailureCount": 842
},
"vllm": {
"attributableFailureCount": 231,
"attributableFailureCount": 232,
"decisionFailureRate": 0.9957,
"decisionSuccessRate": 0.0043,
"decisionTotal": 232,
"decisionTotal": 233,
"failureBreakdown": {
"ambiguous_runtime": 150,
"backend_operator": 25,
"ambiguous_runtime": 151,
"backend_operator": 26,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
"model_load": 18,
@@ -2336,15 +2336,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 403,
"failureCount": 405,
"failureRate": 0.9975,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 1,
"successRate": 0.0025,
"total": 404,
"unresolvedFailureCount": 171
"total": 406,
"unresolvedFailureCount": 172
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2447,7 +2447,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T08:19:33.972825+00:00",
"generatedAt": "2026-09-10T08:28:01.484104+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2654,27 +2654,27 @@
"unresolvedFailureCount": 83
},
"MetaX_c-500": {
"attributableFailureCount": 40,
"decisionFailureRate": 0.8,
"decisionSuccessRate": 0.2,
"decisionTotal": 50,
"attributableFailureCount": 41,
"decisionFailureRate": 0.8039,
"decisionSuccessRate": 0.1961,
"decisionTotal": 51,
"failureBreakdown": {
"ambiguous_runtime": 7,
"backend_operator": 21,
"backend_operator": 22,
"framework_architecture_unsupported": 14,
"memory_capacity": 1,
"model_load": 4,
"参数/模板问题": 17,
"验证失败": 48
},
"failureCount": 112,
"failureRate": 0.918,
"failureCount": 113,
"failureRate": 0.9187,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 10,
"successRate": 0.082,
"total": 122,
"successRate": 0.0813,
"total": 123,
"unresolvedFailureCount": 72
},
"Mthreads_s4000": {
@@ -2683,7 +2683,7 @@
"decisionSuccessRate": 0.0606,
"decisionTotal": 33,
"failureBreakdown": {
"ambiguous_runtime": 23,
"ambiguous_runtime": 24,
"backend_operator": 2,
"framework_architecture_unsupported": 22,
"memory_capacity": 1,
@@ -2693,15 +2693,15 @@
"参数/模板问题": 7,
"验证失败": 26
},
"failureCount": 87,
"failureRate": 0.9775,
"failureCount": 88,
"failureRate": 0.9778,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0225,
"total": 89,
"unresolvedFailureCount": 56
"successRate": 0.0222,
"total": 90,
"unresolvedFailureCount": 57
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 30,
@@ -3525,15 +3525,15 @@
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 11,
"decisionFailureRate": 0.9167,
"decisionSuccessRate": 0.0833,
"decisionTotal": 12,
"attributableFailureCount": 12,
"decisionFailureRate": 0.9231,
"decisionSuccessRate": 0.0769,
"decisionTotal": 13,
"failureBreakdown": {
"backend_operator": 11
"backend_operator": 12
},
"failureCount": 11,
"failureRate": 0.9167,
"failureCount": 12,
"failureRate": 0.9231,
"framework": "vllm",
"modelType": "llama",
"pendingCount": 0,
@@ -3541,10 +3541,10 @@
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 1,
"successRate": 0.0833,
"successRate": 0.0769,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 12,
"total": 13,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|phi3small|compressed-tensors": {
@@ -4436,17 +4436,17 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 4,
"ambiguous_runtime": 5,
"backend_operator": 1,
"framework_architecture_unsupported": 1,
"model_load": 1,
"runtime_memory": 1
},
"failureCount": 8,
"failureCount": 9,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T04:09:13.117076+00:00",
"lastTerminalAt": "2026-09-10T08:28:01.218218+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4454,8 +4454,8 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 8,
"unresolvedFailureCount": 4
"total": 9,
"unresolvedFailureCount": 5
},
"Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -4541,10 +4541,10 @@
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {
"参数/模板问题": 2
"参数/模板问题": 1
},
"failureCount": 2,
"failureRate": 0.6667,
"failureCount": 1,
"failureRate": 0.5,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-07T22:32:11.428244+00:00",
@@ -4552,11 +4552,11 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.3333,
"successRate": 0.5,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 2
"total": 2,
"unresolvedFailureCount": 1
},
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 1,
@@ -6410,14 +6410,14 @@
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors|33": {
"attributableFailureCount": 5,
"attributableFailureCount": 6,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"decisionTotal": 6,
"failureBreakdown": {
"backend_operator": 5
"backend_operator": 6
},
"failureCount": 5,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
@@ -6430,7 +6430,7 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 5,
"total": 6,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|phi3small|compressed-tensors|33": {
@@ -6986,16 +6986,16 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1539,
"totalRecords": 1626,
"terminalRecords": 1541,
"totalRecords": 1628,
"totals": {
"attributableFailureCount": 401,
"decisionFailureRate": 0.8872,
"decisionSuccessRate": 0.1128,
"decisionTotal": 452,
"attributableFailureCount": 402,
"decisionFailureRate": 0.8874,
"decisionSuccessRate": 0.1126,
"decisionTotal": 453,
"failureBreakdown": {
"ambiguous_runtime": 317,
"backend_operator": 30,
"ambiguous_runtime": 318,
"backend_operator": 31,
"framework_architecture_unsupported": 271,
"memory_capacity": 11,
"model_load": 46,
@@ -7006,21 +7006,21 @@
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1488,
"failureCount": 1490,
"failureRate": 0.9669,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 51,
"successRate": 0.0331,
"total": 1539,
"unresolvedFailureCount": 1085
"total": 1541,
"unresolvedFailureCount": 1086
},
"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。",
@@ -7028,7 +7028,7 @@
"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。",
@@ -7049,6 +7049,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1626,
"summarizedRecords": 1628,
"version": 1
}