state: generation 18319 (cycle)

This commit is contained in:
2026-09-29 08:35:06 +00:00
parent 886d47f29e
commit b7f2ccbc37
10 changed files with 1469 additions and 1474 deletions

View File

@@ -3280,7 +3280,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-29T08:20:12.366054+00:00",
"generatedAt": "2026-09-29T08:31:22.010121+00:00",
"summary": {
"activeBlockCount": 165,
"byGpuFramework": {

View File

@@ -1,8 +1,8 @@
{
"communityAttemptedAt": "2026-09-29T08:15:30.056315+00:00",
"communityAttemptedAt": "2026-09-29T08:33:47.852558+00:00",
"communityError": null,
"communitySample": {},
"communityUpdatedAt": "2026-09-29T08:15:30.056315+00:00",
"communityUpdatedAt": "2026-09-29T08:33:47.852558+00:00",
"frameworkAttemptedAt": "2026-09-29T08:15:30.056315+00:00",
"frameworkError": null,
"frameworkStats": {
@@ -434,7 +434,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-29T08:29:53.752017+00:00",
"generatedAt": "2026-09-29T08:33:47.852558+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-09-29T08:29:53.752017+00:00",
"catalogUpdatedAt": "2026-09-29T08:33:47.852558+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-09-29T08:29:53.752017+00:00",
"generatedAt": "2026-09-29T08:33:47.852558+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -6311,6 +6311,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-09-29T08:29:53.752017+00:00",
"taskTreeUpdatedAt": "2026-09-29T08:33:47.852558+00:00",
"version": 1
}

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-29T08:08:03.066000+00:00",
"lastSyncTime": "2026-09-29T08:08:02.743471+00:00",
"generatedAt": "2026-09-29T08:31:21.922543+00:00",
"lastSyncTime": "2026-09-29T08:31:21.660441+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -4944,10 +4944,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 144,
"ambiguous_runtime": 145,
"参数/模板问题": 3
},
"failureCount": 147,
"failureCount": 148,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -4957,8 +4957,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 147,
"unresolvedFailureCount": 147
"total": 148,
"unresolvedFailureCount": 148
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 61,
@@ -5429,21 +5429,21 @@
"failureBreakdown": {
"backend_operator": 9,
"framework_architecture_unsupported": 16,
"platform_infrastructure": 21,
"platform_infrastructure": 22,
"tokenizer_compatibility": 91,
"参数/模板问题": 6
},
"failureCount": 143,
"failureCount": 144,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 21,
"platformFailureCount": 22,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 143,
"total": 144,
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -6105,24 +6105,24 @@
"decisionSuccessRate": 0.0314,
"decisionTotal": 159,
"failureBreakdown": {
"ambiguous_runtime": 326,
"ambiguous_runtime": 327,
"backend_operator": 9,
"framework_architecture_unsupported": 35,
"memory_capacity": 10,
"model_load": 9,
"platform_infrastructure": 21,
"platform_infrastructure": 22,
"tokenizer_compatibility": 91,
"参数/模板问题": 13
},
"failureCount": 514,
"failureCount": 516,
"failureRate": 0.9904,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 21,
"platformFailureCount": 22,
"successCount": 5,
"successRate": 0.0096,
"total": 519,
"unresolvedFailureCount": 339
"total": 521,
"unresolvedFailureCount": 340
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 129,
@@ -6153,7 +6153,7 @@
"unresolvedFailureCount": 197
}
},
"generatedAt": "2026-09-29T08:08:03.050140+00:00",
"generatedAt": "2026-09-29T08:31:21.909443+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 102,
@@ -6384,7 +6384,7 @@
"decisionSuccessRate": 0.066,
"decisionTotal": 106,
"failureBreakdown": {
"ambiguous_runtime": 232,
"ambiguous_runtime": 233,
"backend_operator": 23,
"framework_architecture_unsupported": 37,
"memory_capacity": 3,
@@ -6397,15 +6397,15 @@
"日志缺失": 1,
"验证失败": 23
},
"failureCount": 402,
"failureCount": 403,
"failureRate": 0.9829,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 7,
"successRate": 0.0171,
"total": 409,
"unresolvedFailureCount": 302
"total": 410,
"unresolvedFailureCount": 303
},
"Kunlunxin_r-200-8f": {
"attributableFailureCount": 0,
@@ -6499,21 +6499,21 @@
"context_length": 39,
"framework_architecture_unsupported": 161,
"memory_capacity": 113,
"platform_infrastructure": 229,
"platform_infrastructure": 230,
"repository_structure": 83,
"runtime_memory": 1,
"tokenizer_compatibility": 274,
"参数/模板问题": 228,
"验证失败": 32
},
"failureCount": 1403,
"failureRate": 0.9378,
"failureCount": 1404,
"failureRate": 0.9379,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 229,
"platformFailureCount": 230,
"successCount": 93,
"successRate": 0.0622,
"total": 1496,
"successRate": 0.0621,
"total": 1497,
"unresolvedFailureCount": 422
},
"Vastai_va16": {
@@ -17719,9 +17719,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen2",
@@ -17733,8 +17733,8 @@
"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|qwen3_5_moe|compressed-tensors": {
"attributableFailureCount": 0,
@@ -23812,28 +23812,28 @@
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"consecutivePlatformFailures": 0,
"consecutivePlatformFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"failureBreakdown": {
"framework_architecture_unsupported": 1,
"platform_infrastructure": 2,
"platform_infrastructure": 3,
"tokenizer_compatibility": 5
},
"failureCount": 8,
"failureCount": 9,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": "2026-09-23T02:14:08+00:00",
"lastTerminalAt": "2026-09-26T19:06:57.060378+00:00",
"lastPlatformFailureAt": "2026-09-29T08:28:09+00:00",
"lastTerminalAt": "2026-09-29T08:31:21.660441+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"platformFailureCount": 3,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 8,
"total": 9,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -23894,9 +23894,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"参数/模板问题": 9
"参数/模板问题": 8
},
"failureCount": 9,
"failureCount": 8,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
@@ -23908,8 +23908,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 9,
"unresolvedFailureCount": 9
"total": 8,
"unresolvedFailureCount": 8
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
"attributableFailureCount": 5,
@@ -43859,9 +43859,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 31,
@@ -43874,8 +43874,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen2|none|34": {
"attributableFailureCount": 0,
@@ -52329,15 +52329,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17099,
"totalRecords": 17320,
"terminalRecords": 17101,
"totalRecords": 17322,
"totals": {
"attributableFailureCount": 6130,
"decisionFailureRate": 0.8636,
"decisionSuccessRate": 0.1364,
"decisionTotal": 7098,
"failureBreakdown": {
"ambiguous_runtime": 4438,
"ambiguous_runtime": 4439,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
@@ -52345,7 +52345,7 @@
"framework_architecture_unsupported": 2184,
"memory_capacity": 1206,
"model_load": 550,
"platform_infrastructure": 940,
"platform_infrastructure": 941,
"repository_structure": 742,
"runtime_memory": 101,
"tokenizer_compatibility": 682,
@@ -52353,15 +52353,15 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16131,
"failureCount": 16133,
"failureRate": 0.9434,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 940,
"platformFailureCount": 941,
"successCount": 968,
"successRate": 0.0566,
"total": 17099,
"unresolvedFailureCount": 9061
"total": 17101,
"unresolvedFailureCount": 9062
},
"warnings": [
"GPU Ascend_910-b3 本地统计失败率偏高(≥50%),建议重点关注。",
@@ -52390,7 +52390,6 @@
"组合 Kunlunxin_p-800|vllm_tokenizer_patch|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|llamacpp|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|unknown|visual-multi-modal 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Kunlunxin_p-800|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 MetaX_c-500|vllm|visual-multi-modal 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。",
"组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -52415,10 +52414,11 @@
"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 Cambricon_mlu-370-x4|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 Ascend_910-b3|vllm_tokenizer_patch|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"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 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 Kunlunxin_p-800|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17320,
"summarizedRecords": 17322,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"failReason": "platform_infrastructure", "failureAction": "open_short_gpu_framework_circuit_and_retry_other_models", "failureCategory": "platform_infrastructure", "failureClassificationReason": "no_idle_device", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-29T08:31:21.660441+00:00", "modelId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-29T08:28:09+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4458938", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm", "lastSyncTime": "2026-09-29T08:08:02.743424+00:00", "modelId": "siliconflow/gpt-oss-20b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-29T08:00:09+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4579600", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-26T19:06:57.060378+00:00", "modelId": "RedHatAI/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-26T19:06:08+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4458001", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-26T17:57:36.159288+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-Non-Uniform-compressed-tensors", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-26T17:52:08+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457999", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T02:55:04.446646+00:00", "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T02:53:07+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969661", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T02:55:04.446677+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T02:53:07+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4754068", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T02:55:04.446703+00:00", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T02:53:07+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4939007", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T02:55:04.446712+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T02:53:07+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4923872", "taskType": "text-generation", "verifyResult": null}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff