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

state: generation 6138 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-12 09:47:35 +00:00
parent 1bff199c70
commit d794c7d231
9 changed files with 2298 additions and 2295 deletions
Download Patch File Download Diff File Expand all files Collapse all files

121
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-12T09:16:13.625860+00:00",
"lastSyncTime": "2026-09-12T09:16:13.411459+00:00",
"generatedAt": "2026-09-12T09:44:49.370347+00:00",
"lastSyncTime": "2026-09-12T09:44:49.014208+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1523,13 +1523,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 39,
"failureBreakdown": {
"ambiguous_runtime": 34,
"ambiguous_runtime": 35,
"framework_architecture_unsupported": 35,
"memory_capacity": 1,
"repository_structure": 1,
"tokenizer_compatibility": 2
},
"failureCount": 73,
"failureCount": 74,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1539,8 +1539,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 73,
"unresolvedFailureCount": 34
"total": 74,
"unresolvedFailureCount": 35
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 27,
@@ -1979,29 +1979,30 @@
"unresolvedFailureCount": 56
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 48,
"decisionFailureRate": 0.9412,
"decisionSuccessRate": 0.0588,
"decisionTotal": 51,
"attributableFailureCount": 49,
"decisionFailureRate": 0.9423,
"decisionSuccessRate": 0.0577,
"decisionTotal": 52,
"failureBreakdown": {
"ambiguous_runtime": 8,
"backend_operator": 27,
"framework_architecture_unsupported": 15,
"memory_capacity": 1,
"model_load": 5,
"repository_structure": 1,
"参数/模板问题": 9
},
"failureCount": 65,
"failureRate": 0.9559,
"failureCount": 66,
"failureRate": 0.9565,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 3,
"successRate": 0.0441,
"successRate": 0.0435,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 68,
"total": 69,
"unresolvedFailureCount": 17
},
"Mthreads_s4000|llamacpp|text-generation": {
@@ -2394,31 +2395,31 @@
"unresolvedFailureCount": 864
},
"vllm": {
"attributableFailureCount": 265,
"attributableFailureCount": 266,
"decisionFailureRate": 0.9888,
"decisionSuccessRate": 0.0112,
"decisionTotal": 268,
"decisionTotal": 269,
"failureBreakdown": {
"ambiguous_runtime": 198,
"ambiguous_runtime": 199,
"backend_operator": 34,
"framework_architecture_unsupported": 182,
"memory_capacity": 6,
"model_load": 24,
"platform_infrastructure": 1,
"repository_structure": 7,
"repository_structure": 8,
"runtime_memory": 6,
"tokenizer_compatibility": 6,
"参数/模板问题": 24
},
"failureCount": 488,
"failureCount": 490,
"failureRate": 0.9939,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0061,
"total": 491,
"unresolvedFailureCount": 222
"total": 493,
"unresolvedFailureCount": 223
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2522,7 +2523,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T09:16:13.620568+00:00",
"generatedAt": "2026-09-12T09:44:49.366507+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2553,7 +2554,7 @@
"decisionSuccessRate": 0.0476,
"decisionTotal": 42,
"failureBreakdown": {
"ambiguous_runtime": 35,
"ambiguous_runtime": 36,
"framework_architecture_unsupported": 35,
"memory_capacity": 1,
"model_load": 1,
@@ -2562,15 +2563,15 @@
"参数/模板问题": 12,
"验证失败": 175
},
"failureCount": 262,
"failureRate": 0.9924,
"failureCount": 263,
"failureRate": 0.9925,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0076,
"total": 264,
"unresolvedFailureCount": 222
"successRate": 0.0075,
"total": 265,
"unresolvedFailureCount": 223
},
"Biren_166m": {
"attributableFailureCount": 28,
@@ -2731,27 +2732,28 @@
"unresolvedFailureCount": 91
},
"MetaX_c-500": {
"attributableFailureCount": 48,
"decisionFailureRate": 0.8,
"decisionSuccessRate": 0.2,
"decisionTotal": 60,
"attributableFailureCount": 49,
"decisionFailureRate": 0.8033,
"decisionSuccessRate": 0.1967,
"decisionTotal": 61,
"failureBreakdown": {
"ambiguous_runtime": 8,
"backend_operator": 27,
"framework_architecture_unsupported": 15,
"memory_capacity": 1,
"model_load": 5,
"repository_structure": 1,
"参数/模板问题": 17,
"验证失败": 48
},
"failureCount": 121,
"failureRate": 0.9098,
"failureCount": 122,
"failureRate": 0.9104,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 12,
"successRate": 0.0902,
"total": 133,
"successRate": 0.0896,
"total": 134,
"unresolvedFailureCount": 73
},
"Mthreads_s4000": {
@@ -4291,7 +4293,7 @@
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T08:56:30.820631+00:00",
"lastTerminalAt": "2026-09-12T09:44:49.014179+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4538,22 +4540,23 @@
"unresolvedFailureCount": 19
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 3,
"model_load": 1
"model_load": 1,
"repository_structure": 1
},
"failureCount": 5,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T06:34:23.913239+00:00",
"lastTerminalAt": "2026-09-12T09:44:49.014208+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4561,7 +4564,7 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 5,
"total": 6,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|llamacpp|text-generation": {
@@ -7183,41 +7186,40 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1709,
"totalRecords": 1796,
"terminalRecords": 1711,
"totalRecords": 1798,
"totals": {
"attributableFailureCount": 474,
"decisionFailureRate": 0.8927,
"decisionSuccessRate": 0.1073,
"decisionTotal": 531,
"attributableFailureCount": 475,
"decisionFailureRate": 0.8929,
"decisionSuccessRate": 0.1071,
"decisionTotal": 532,
"failureBreakdown": {
"ambiguous_runtime": 400,
"ambiguous_runtime": 401,
"backend_operator": 42,
"framework_architecture_unsupported": 290,
"memory_capacity": 11,
"model_load": 70,
"platform_infrastructure": 4,
"repository_structure": 7,
"repository_structure": 8,
"runtime_memory": 6,
"tokenizer_compatibility": 48,
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1652,
"failureRate": 0.9666,
"failureCount": 1654,
"failureRate": 0.9667,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 57,
"successRate": 0.0334,
"total": 1709,
"unresolvedFailureCount": 1174
"successRate": 0.0333,
"total": 1711,
"unresolvedFailureCount": 1175
},
"warnings": [
"GPU Ascend_910-b3 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 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 Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -7226,6 +7228,7 @@
"GPU MetaX_c-500 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 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 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。",
"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 Ascend_910-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -7247,6 +7250,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1796,
"summarizedRecords": 1798,
"version": 1
}