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

state: generation 4818 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-09 22:42:56 +00:00
parent a98a9fcf94
commit 896196873a
9 changed files with 2440 additions and 2419 deletions
Download Patch File Download Diff File Expand all files Collapse all files

126
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-09T22:24:28.440996+00:00",
"lastSyncTime": "2026-09-09T22:24:28.408286+00:00",
"generatedAt": "2026-09-09T22:41:00.047359+00:00",
"lastSyncTime": "2026-09-09T22:40:59.810547+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1906,19 +1906,19 @@
"unresolvedFailureCount": 56
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 34,
"attributableFailureCount": 36,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 34,
"decisionTotal": 36,
"failureBreakdown": {
"ambiguous_runtime": 7,
"backend_operator": 15,
"backend_operator": 17,
"framework_architecture_unsupported": 14,
"memory_capacity": 1,
"model_load": 4,
"参数/模板问题": 9
},
"failureCount": 50,
"failureCount": 52,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1928,7 +1928,7 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 50,
"total": 52,
"unresolvedFailureCount": 16
},
"Mthreads_s4000|llamacpp|text-generation": {
@@ -2315,13 +2315,13 @@
"unresolvedFailureCount": 818
},
"vllm": {
"attributableFailureCount": 223,
"attributableFailureCount": 225,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 223,
"decisionTotal": 225,
"failureBreakdown": {
"ambiguous_runtime": 116,
"backend_operator": 18,
"backend_operator": 20,
"framework_architecture_unsupported": 168,
"memory_capacity": 6,
"model_load": 18,
@@ -2331,14 +2331,14 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 361,
"failureCount": 363,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"total": 361,
"total": 363,
"unresolvedFailureCount": 137
},
"vllm-mlu": {
@@ -2442,7 +2442,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-09T22:24:28.437080+00:00",
"generatedAt": "2026-09-09T22:41:00.042625+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2649,27 +2649,27 @@
"unresolvedFailureCount": 72
},
"MetaX_c-500": {
"attributableFailureCount": 34,
"decisionFailureRate": 0.7907,
"decisionSuccessRate": 0.2093,
"decisionTotal": 43,
"attributableFailureCount": 36,
"decisionFailureRate": 0.8,
"decisionSuccessRate": 0.2,
"decisionTotal": 45,
"failureBreakdown": {
"ambiguous_runtime": 7,
"backend_operator": 15,
"backend_operator": 17,
"framework_architecture_unsupported": 14,
"memory_capacity": 1,
"model_load": 4,
"参数/模板问题": 17,
"验证失败": 48
},
"failureCount": 106,
"failureRate": 0.9217,
"failureCount": 108,
"failureRate": 0.9231,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 9,
"successRate": 0.0783,
"total": 115,
"successRate": 0.0769,
"total": 117,
"unresolvedFailureCount": 72
},
"Mthreads_s4000": {
@@ -3453,14 +3453,14 @@
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 7,
"attributableFailureCount": 8,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"decisionTotal": 8,
"failureBreakdown": {
"backend_operator": 7
"backend_operator": 8
},
"failureCount": 7,
"failureCount": 8,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "llama",
@@ -3472,7 +3472,7 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 7,
"total": 8,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|phi3small|compressed-tensors": {
@@ -3614,14 +3614,14 @@
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 4,
"attributableFailureCount": 5,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"decisionTotal": 5,
"failureBreakdown": {
"backend_operator": 4
"backend_operator": 5
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "starcoder2",
@@ -3633,7 +3633,7 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 4,
"total": 5,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|glm_ocr|fp8": {
@@ -6079,14 +6079,14 @@
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors|30": {
"attributableFailureCount": 2,
"attributableFailureCount": 3,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {
"backend_operator": 2
"backend_operator": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 30,
@@ -6099,7 +6099,7 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors|33": {
@@ -6342,6 +6342,30 @@
"total": 2,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"backend_operator": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
"modelType": "starcoder2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -6655,16 +6679,16 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1452,
"totalRecords": 1536,
"terminalRecords": 1454,
"totalRecords": 1538,
"totals": {
"attributableFailureCount": 386,
"decisionFailureRate": 0.8894,
"decisionSuccessRate": 0.1106,
"decisionTotal": 434,
"attributableFailureCount": 388,
"decisionFailureRate": 0.8899,
"decisionSuccessRate": 0.1101,
"decisionTotal": 436,
"failureBreakdown": {
"ambiguous_runtime": 249,
"backend_operator": 21,
"backend_operator": 23,
"framework_architecture_unsupported": 266,
"memory_capacity": 11,
"model_load": 45,
@@ -6675,21 +6699,21 @@
"参数/模板问题": 94,
"验证失败": 673
},
"failureCount": 1404,
"failureRate": 0.9669,
"failureCount": 1406,
"failureRate": 0.967,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 48,
"successRate": 0.0331,
"total": 1452,
"successRate": 0.033,
"total": 1454,
"unresolvedFailureCount": 1016
},
"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。",
@@ -6697,7 +6721,7 @@
"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。",
@@ -6718,6 +6742,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1536,
"summarizedRecords": 1538,
"version": 1
}