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

state: generation 21751 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-07 07:01:41 +00:00
parent 2c3c50572d
commit b33a51296a
11 changed files with 2946 additions and 3468 deletions
Download Patch File Download Diff File Expand all files Collapse all files

187
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-07T06:31:48.041351+00:00",
"lastSyncTime": "2026-10-07T06:31:47.977081+00:00",
"generatedAt": "2026-10-07T06:48:39.332067+00:00",
"lastSyncTime": "2026-10-07T06:48:39.066266+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1843,6 +1843,25 @@
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation"
},
"iluvatar_mrv-100|vllm|text-generation|model_type:gpt_oss": {
"architectureSignature": "model_type:gpt_oss",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-11-05T09:47:42.556514+00:00",
"framework": "vllm",
"latestFailureAt": "2026-10-06T09:47:42.556514+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "gpt_oss",
"sourceModelIds": [
"mlx-community/gpt-oss-20b-OptiQ-4bit"
],
"sourceTaskIds": [
"5321077"
],
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation"
},
"kunlunxin_p-800|vllm_tokenizer_patch|text-generation|architectures:bailingmoev2_5forcausallm": {
"architectureSignature": "architectures:bailingmoev2_5forcausallm",
"architectures": [
@@ -2822,7 +2841,7 @@
}
},
"architectureCompatibilitySummary": {
"activeBlockCount": 142,
"activeBlockCount": 143,
"byGpuFramework": {
"Ascend_910-b3|vllm": 9,
"Ascend_910-b3|vllm_tokenizer_patch": 7,
@@ -2838,6 +2857,7 @@
"Iluvatar_bi-150|vllm": 6,
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 3,
"Iluvatar_bi-150|vllm_tokenizer_patch": 2,
"Iluvatar_mrv-100|vllm": 1,
"Kunlunxin_p-800|vllm": 10,
"Kunlunxin_p-800|vllm_tokenizer_patch": 9,
"MetaX_c-500|vllm": 1,
@@ -4411,27 +4431,27 @@
"unresolvedFailureCount": 57
},
"Iluvatar_mrv-100|vllm|text-generation": {
"attributableFailureCount": 33,
"decisionFailureRate": 0.6735,
"decisionSuccessRate": 0.3265,
"decisionTotal": 49,
"attributableFailureCount": 34,
"decisionFailureRate": 0.68,
"decisionSuccessRate": 0.32,
"decisionTotal": 50,
"failureBreakdown": {
"ambiguous_runtime": 13,
"framework_architecture_unsupported": 28,
"framework_architecture_unsupported": 29,
"model_load": 4,
"tokenizer_compatibility": 1
},
"failureCount": 46,
"failureRate": 0.7419,
"failureCount": 47,
"failureRate": 0.746,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 16,
"successRate": 0.2581,
"successRate": 0.254,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 62,
"total": 63,
"unresolvedFailureCount": 13
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -5542,17 +5562,17 @@
"unresolvedFailureCount": 6477
},
"vllm": {
"attributableFailureCount": 3668,
"attributableFailureCount": 3669,
"decisionFailureRate": 0.9722,
"decisionSuccessRate": 0.0278,
"decisionTotal": 3773,
"decisionTotal": 3774,
"failureBreakdown": {
"ambiguous_runtime": 1601,
"architecture_compatibility": 112,
"attention_backend": 3,
"backend_operator": 94,
"context_length": 161,
"framework_architecture_unsupported": 1389,
"framework_architecture_unsupported": 1390,
"memory_capacity": 725,
"model_load": 228,
"platform_infrastructure": 879,
@@ -5561,14 +5581,14 @@
"tokenizer_compatibility": 420,
"参数/模板问题": 50
},
"failureCount": 6198,
"failureCount": 6199,
"failureRate": 0.9833,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 879,
"successCount": 105,
"successRate": 0.0167,
"total": 6303,
"total": 6304,
"unresolvedFailureCount": 1651
},
"vllm-customized": {
@@ -5719,7 +5739,7 @@
"unresolvedFailureCount": 237
}
},
"generatedAt": "2026-10-07T06:31:48.024636+00:00",
"generatedAt": "2026-10-07T06:48:39.315587+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 119,
@@ -5915,16 +5935,16 @@
"unresolvedFailureCount": 1166
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 983,
"decisionFailureRate": 0.8474,
"decisionSuccessRate": 0.1526,
"decisionTotal": 1160,
"attributableFailureCount": 984,
"decisionFailureRate": 0.8475,
"decisionSuccessRate": 0.1525,
"decisionTotal": 1161,
"failureBreakdown": {
"ambiguous_runtime": 353,
"architecture_compatibility": 47,
"backend_operator": 1,
"context_length": 77,
"framework_architecture_unsupported": 300,
"framework_architecture_unsupported": 301,
"memory_capacity": 219,
"model_load": 88,
"platform_infrastructure": 7,
@@ -5935,14 +5955,14 @@
"日志缺失": 6,
"验证失败": 47
},
"failureCount": 1712,
"failureCount": 1713,
"failureRate": 0.9063,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 7,
"successCount": 177,
"successRate": 0.0937,
"total": 1889,
"total": 1890,
"unresolvedFailureCount": 722
},
"Kunlunxin_p-800": {
@@ -17397,6 +17417,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|gpt_oss|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "gpt_oss",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|hrm_text|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -25187,9 +25230,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"参数/模板问题": 3
"参数/模板问题": 2
},
"failureCount": 3,
"failureCount": 2,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
@@ -25201,8 +25244,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 2,
"unresolvedFailureCount": 2
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 0,
@@ -25620,20 +25663,21 @@
"unresolvedFailureCount": 2
},
"Iluvatar_mrv-100|vllm|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-22T23:51:40.058287+00:00",
"lastTerminalAt": "2026-10-07T06:48:39.066266+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -25641,7 +25685,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -28087,6 +28131,31 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|gpt_oss|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-10-07T06:48:39.066266+00:00",
"modelType": "gpt_oss",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -46499,6 +46568,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|gpt_oss|none|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
"modelType": "gpt_oss",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|hrm_text|none|31": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -58280,20 +58373,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17360,
"totalRecords": 17617,
"terminalRecords": 17361,
"totalRecords": 17618,
"totals": {
"attributableFailureCount": 6243,
"attributableFailureCount": 6244,
"decisionFailureRate": 0.8646,
"decisionSuccessRate": 0.1354,
"decisionTotal": 7221,
"decisionTotal": 7222,
"failureBreakdown": {
"ambiguous_runtime": 4559,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 129,
"context_length": 327,
"framework_architecture_unsupported": 2265,
"framework_architecture_unsupported": 2266,
"memory_capacity": 1206,
"model_load": 569,
"platform_infrastructure": 952,
@@ -58304,14 +58397,14 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16382,
"failureCount": 16383,
"failureRate": 0.9437,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 952,
"successCount": 978,
"successRate": 0.0563,
"total": 17360,
"total": 17361,
"unresolvedFailureCount": 9187
},
"warnings": [
@@ -58321,14 +58414,14 @@
"GPU hygon_k100-ai 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 Ascend_910-b3 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_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Kunlunxin_p-800 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 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 Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-100 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 Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
"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 Ascend_910-b3|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_mrv-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -58373,6 +58466,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17617,
"summarizedRecords": 17618,
"version": 1
}