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

state: generation 5066 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 08:04:08 +00:00
parent d0d67f0faf
commit 54d7a176c4
11 changed files with 2033 additions and 2129 deletions
Download Patch File Download Diff File Expand all files Collapse all files

180
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T07:53:10.960863+00:00",
"lastSyncTime": "2026-09-10T07:53:10.699435+00:00",
"generatedAt": "2026-09-10T08:02:07.265881+00:00",
"lastSyncTime": "2026-09-10T08:02:07.004701+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1872,10 +1872,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 24,
"ambiguous_runtime": 25,
"参数/模板问题": 1
},
"failureCount": 25,
"failureCount": 26,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -1885,8 +1885,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 25,
"unresolvedFailureCount": 25
"total": 26,
"unresolvedFailureCount": 26
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -1911,29 +1911,29 @@
"unresolvedFailureCount": 56
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 39,
"decisionFailureRate": 0.975,
"decisionSuccessRate": 0.025,
"decisionTotal": 40,
"attributableFailureCount": 40,
"decisionFailureRate": 0.9756,
"decisionSuccessRate": 0.0244,
"decisionTotal": 41,
"failureBreakdown": {
"ambiguous_runtime": 7,
"backend_operator": 20,
"backend_operator": 21,
"framework_architecture_unsupported": 14,
"memory_capacity": 1,
"model_load": 4,
"参数/模板问题": 9
},
"failureCount": 55,
"failureRate": 0.9821,
"failureCount": 56,
"failureRate": 0.9825,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0179,
"successRate": 0.0175,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 56,
"total": 57,
"unresolvedFailureCount": 16
},
"Mthreads_s4000|llamacpp|text-generation": {
@@ -2320,13 +2320,13 @@
"unresolvedFailureCount": 841
},
"vllm": {
"attributableFailureCount": 230,
"attributableFailureCount": 231,
"decisionFailureRate": 0.9957,
"decisionSuccessRate": 0.0043,
"decisionTotal": 231,
"decisionTotal": 232,
"failureBreakdown": {
"ambiguous_runtime": 150,
"backend_operator": 24,
"backend_operator": 25,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
"model_load": 18,
@@ -2336,14 +2336,14 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 402,
"failureCount": 403,
"failureRate": 0.9975,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 1,
"successRate": 0.0025,
"total": 403,
"total": 404,
"unresolvedFailureCount": 171
},
"vllm-mlu": {
@@ -2411,22 +2411,22 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 32,
"failureBreakdown": {
"ambiguous_runtime": 25,
"ambiguous_runtime": 26,
"framework_architecture_unsupported": 4,
"model_load": 1,
"platform_infrastructure": 1,
"tokenizer_compatibility": 27,
"参数/模板问题": 7
},
"failureCount": 65,
"failureCount": 66,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"total": 65,
"unresolvedFailureCount": 32
"total": 66,
"unresolvedFailureCount": 33
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 0,
@@ -2447,7 +2447,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T07:53:10.956424+00:00",
"generatedAt": "2026-09-10T08:02:07.261719+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2638,43 +2638,43 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 56,
"ambiguous_runtime": 57,
"memory_capacity": 1,
"参数/模板问题": 1,
"验证失败": 23
},
"failureCount": 81,
"failureCount": 82,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 81,
"unresolvedFailureCount": 80
"total": 82,
"unresolvedFailureCount": 81
},
"MetaX_c-500": {
"attributableFailureCount": 39,
"decisionFailureRate": 0.7959,
"decisionSuccessRate": 0.2041,
"decisionTotal": 49,
"attributableFailureCount": 40,
"decisionFailureRate": 0.8,
"decisionSuccessRate": 0.2,
"decisionTotal": 50,
"failureBreakdown": {
"ambiguous_runtime": 7,
"backend_operator": 20,
"backend_operator": 21,
"framework_architecture_unsupported": 14,
"memory_capacity": 1,
"model_load": 4,
"参数/模板问题": 17,
"验证失败": 48
},
"failureCount": 111,
"failureRate": 0.9174,
"failureCount": 112,
"failureRate": 0.918,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 10,
"successRate": 0.0826,
"total": 121,
"successRate": 0.082,
"total": 122,
"unresolvedFailureCount": 72
},
"Mthreads_s4000": {
@@ -3279,9 +3279,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 6
"ambiguous_runtime": 7
},
"failureCount": 6,
"failureCount": 7,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "llama",
@@ -3293,8 +3293,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 6,
"unresolvedFailureCount": 6
"total": 7,
"unresolvedFailureCount": 7
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|phi3small|compressed-tensors": {
"attributableFailureCount": 0,
@@ -3504,15 +3504,15 @@
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 10,
"decisionFailureRate": 0.9091,
"decisionSuccessRate": 0.0909,
"decisionTotal": 11,
"attributableFailureCount": 11,
"decisionFailureRate": 0.9167,
"decisionSuccessRate": 0.0833,
"decisionTotal": 12,
"failureBreakdown": {
"backend_operator": 10
"backend_operator": 11
},
"failureCount": 10,
"failureRate": 0.9091,
"failureCount": 11,
"failureRate": 0.9167,
"framework": "vllm",
"modelType": "llama",
"pendingCount": 0,
@@ -3520,10 +3520,10 @@
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 1,
"successRate": 0.0909,
"successRate": 0.0833,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 11,
"total": 12,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|phi3small|compressed-tensors": {
@@ -4315,9 +4315,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 12
"ambiguous_runtime": 13
},
"failureCount": 12,
"failureCount": 13,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
@@ -4329,8 +4329,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 12,
"unresolvedFailureCount": 12
"total": 13,
"unresolvedFailureCount": 13
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -4950,9 +4950,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-09T11:33:22.442275+00:00",
@@ -4965,8 +4965,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|phi3small|compressed-tensors": {
"attributableFailureCount": 0,
@@ -5912,6 +5912,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -6319,14 +6343,14 @@
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors|32": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"backend_operator": 1
"backend_operator": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
@@ -6339,7 +6363,7 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors|33": {
@@ -6919,16 +6943,16 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1533,
"totalRecords": 1620,
"terminalRecords": 1535,
"totalRecords": 1622,
"totals": {
"attributableFailureCount": 400,
"decisionFailureRate": 0.8889,
"decisionSuccessRate": 0.1111,
"decisionTotal": 450,
"attributableFailureCount": 401,
"decisionFailureRate": 0.8891,
"decisionSuccessRate": 0.1109,
"decisionTotal": 451,
"failureBreakdown": {
"ambiguous_runtime": 313,
"backend_operator": 29,
"ambiguous_runtime": 314,
"backend_operator": 30,
"framework_architecture_unsupported": 271,
"memory_capacity": 11,
"model_load": 46,
@@ -6939,21 +6963,21 @@
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1483,
"failureCount": 1485,
"failureRate": 0.9674,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 50,
"successRate": 0.0326,
"total": 1533,
"unresolvedFailureCount": 1081
"total": 1535,
"unresolvedFailureCount": 1082
},
"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 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。",
"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。",
@@ -6961,7 +6985,7 @@
"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 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。",
"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。",
@@ -6982,6 +7006,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1620,
"summarizedRecords": 1622,
"version": 1
}