state: generation 10297 (cycle)
This commit is contained in:
@@ -1762,7 +1762,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-20T05:55:54.468145+00:00",
|
||||
"generatedAt": "2026-09-20T05:59:18.968797+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 85,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-20T05:58:17.877507+00:00",
|
||||
"generatedAt": "2026-09-20T05:59:28.194949+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-09-20T05:58:17.877507+00:00",
|
||||
"catalogUpdatedAt": "2026-09-20T05:59:28.194949+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-09-20T05:58:17.877507+00:00",
|
||||
"generatedAt": "2026-09-20T05:59:28.194949+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6553,6 +6553,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-09-20T05:58:17.877507+00:00",
|
||||
"taskTreeUpdatedAt": "2026-09-20T05:59:28.194949+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-20T05:38:37.068183+00:00",
|
||||
"lastSyncTime": "2026-09-20T05:38:36.779422+00:00",
|
||||
"generatedAt": "2026-09-20T05:59:18.919080+00:00",
|
||||
"lastSyncTime": "2026-09-20T05:59:18.862303+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -3299,9 +3299,9 @@
|
||||
},
|
||||
"MetaX_c-500|unknown|text-generation": {
|
||||
"attributableFailureCount": 28,
|
||||
"decisionFailureRate": 0.1972,
|
||||
"decisionSuccessRate": 0.8028,
|
||||
"decisionTotal": 142,
|
||||
"decisionFailureRate": 0.1958,
|
||||
"decisionSuccessRate": 0.8042,
|
||||
"decisionTotal": 143,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 103,
|
||||
"context_length": 13,
|
||||
@@ -3312,16 +3312,16 @@
|
||||
"验证失败": 48
|
||||
},
|
||||
"failureCount": 531,
|
||||
"failureRate": 0.8233,
|
||||
"failureRate": 0.822,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 114,
|
||||
"successRate": 0.1767,
|
||||
"successCount": 115,
|
||||
"successRate": 0.178,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 645,
|
||||
"total": 646,
|
||||
"unresolvedFailureCount": 503
|
||||
},
|
||||
"MetaX_c-500|unknown|unknown": {
|
||||
@@ -4172,9 +4172,9 @@
|
||||
},
|
||||
"unknown": {
|
||||
"attributableFailureCount": 1855,
|
||||
"decisionFailureRate": 0.6976,
|
||||
"decisionSuccessRate": 0.3024,
|
||||
"decisionTotal": 2659,
|
||||
"decisionFailureRate": 0.6974,
|
||||
"decisionSuccessRate": 0.3026,
|
||||
"decisionTotal": 2660,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1962,
|
||||
"architecture_compatibility": 100,
|
||||
@@ -4192,13 +4192,13 @@
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 8301,
|
||||
"failureRate": 0.9117,
|
||||
"failureRate": 0.9116,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 42,
|
||||
"successCount": 804,
|
||||
"successRate": 0.0883,
|
||||
"total": 9105,
|
||||
"successCount": 805,
|
||||
"successRate": 0.0884,
|
||||
"total": 9106,
|
||||
"unresolvedFailureCount": 6404
|
||||
},
|
||||
"vllm": {
|
||||
@@ -4341,7 +4341,7 @@
|
||||
"unresolvedFailureCount": 23
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-20T05:38:37.060555+00:00",
|
||||
"generatedAt": "2026-09-20T05:59:18.912281+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 72,
|
||||
@@ -4606,9 +4606,9 @@
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"attributableFailureCount": 651,
|
||||
"decisionFailureRate": 0.822,
|
||||
"decisionSuccessRate": 0.178,
|
||||
"decisionTotal": 792,
|
||||
"decisionFailureRate": 0.8209,
|
||||
"decisionSuccessRate": 0.1791,
|
||||
"decisionTotal": 793,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 296,
|
||||
"architecture_compatibility": 21,
|
||||
@@ -4625,13 +4625,13 @@
|
||||
"验证失败": 48
|
||||
},
|
||||
"failureCount": 1413,
|
||||
"failureRate": 0.9093,
|
||||
"failureRate": 0.9087,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 5,
|
||||
"successCount": 141,
|
||||
"successRate": 0.0907,
|
||||
"total": 1554,
|
||||
"successCount": 142,
|
||||
"successRate": 0.0913,
|
||||
"total": 1555,
|
||||
"unresolvedFailureCount": 757
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
@@ -9941,23 +9941,23 @@
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 1.0,
|
||||
"decisionTotal": 1,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"参数/模板问题": 2
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureRate": 0.6667,
|
||||
"failureRate": 0.5,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-20T04:34:35.568144+00:00",
|
||||
"lastTerminalAt": "2026-09-20T05:59:18.862303+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.3333,
|
||||
"successCount": 2,
|
||||
"successRate": 0.5,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 3,
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation": {
|
||||
@@ -10069,18 +10069,18 @@
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 11,
|
||||
"consecutiveFailures": 11,
|
||||
"attributableFailureCount": 10,
|
||||
"consecutiveFailures": 10,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 11,
|
||||
"decisionTotal": 10,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 3,
|
||||
"platform_infrastructure": 4,
|
||||
"tokenizer_compatibility": 8
|
||||
"tokenizer_compatibility": 7
|
||||
},
|
||||
"failureCount": 15,
|
||||
"failureCount": 14,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastPlatformFailureAt": "2026-09-16T02:03:21+00:00",
|
||||
@@ -10092,7 +10092,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 15,
|
||||
"total": 14,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
@@ -17945,13 +17945,13 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 15757,
|
||||
"totalRecords": 15860,
|
||||
"terminalRecords": 15758,
|
||||
"totalRecords": 15861,
|
||||
"totals": {
|
||||
"attributableFailureCount": 5701,
|
||||
"decisionFailureRate": 0.8618,
|
||||
"decisionSuccessRate": 0.1382,
|
||||
"decisionTotal": 6615,
|
||||
"decisionFailureRate": 0.8617,
|
||||
"decisionSuccessRate": 0.1383,
|
||||
"decisionTotal": 6616,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3718,
|
||||
"architecture_compatibility": 212,
|
||||
@@ -17970,13 +17970,13 @@
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 14843,
|
||||
"failureRate": 0.942,
|
||||
"failureRate": 0.9419,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 922,
|
||||
"successCount": 914,
|
||||
"successRate": 0.058,
|
||||
"total": 15757,
|
||||
"successCount": 915,
|
||||
"successRate": 0.0581,
|
||||
"total": 15758,
|
||||
"unresolvedFailureCount": 8220
|
||||
},
|
||||
"warnings": [
|
||||
@@ -18020,13 +18020,13 @@
|
||||
"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 Cambricon_mlu-370-x4|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 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 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 Cambricon_mlu-370-x8|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 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。",
|
||||
"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 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 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。"
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 15860,
|
||||
"summarizedRecords": 15861,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-20T05:59:18.862303+00:00", "modelId": "AI-ModelScope/granite-20b-code-base-8k", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-20T05:57:22+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079080", "taskType": "text-generation", "verifyResult": 1}
|
||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-20T04:34:35.568144+00:00", "modelId": "AI-ModelScope/granite-20b-code-instruct", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-20T04:31:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079070", "taskType": "text-generation", "verifyResult": 1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-20T03:09:22.973374+00:00", "modelId": "RedHatAI/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:09:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477835", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-19T23:13:47.695492+00:00", "modelId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-19T23:07:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477839", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -297,4 +298,3 @@
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-12T06:59:46.603354+00:00", "modelId": "nightmedia/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Lite-Preview-Distill-Heretic-qx86-hi-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T06:55:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079259", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-09-17T04:25:23.963454+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-12T06:53:56.898337+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4795839", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T06:34:23.913239+00:00", "modelId": "nightmedia/Qwen3-4B-Thinking-2507-Gemini-3-Pro-Preview-High-Reasoning-Distill-Heretic-qx86-hi-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T06:29:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079116", "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": "2026-09-12T06:34:23.913264+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T06:27:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457993", "taskType": "text-generation", "verifyResult": -1}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -1,24 +1,24 @@
|
||||
{
|
||||
"agentVersion": "2026.09.20.2",
|
||||
"checksums": {
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "6ee5a71c77fa0cd75b827543632beedfe62d1cdb7fa58559affd2e2e9b70a051",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "675628e26810fb1227f76abfc934692cafa80869f331c23f14e2bd12ebcf0e15",
|
||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||
".modelhub_state/market_intelligence.json": "cc5484879f1abc4bb88ec1024003c55ab54c8bdb2aa215e929f231b08ef5499e",
|
||||
".modelhub_state/official_capabilities.json": "79368caaeab916837924875ab1d301021d4e68ac32eb5e2b2d5006d66e0d57d0",
|
||||
".modelhub_state/outcome_checkpoint.json": "7978a6d4c4393600c4ad9ebabb89d834c304de4848ac4670aef26b9964153815",
|
||||
".modelhub_state/market_intelligence.json": "5fa944ece945824eddbeb87c3e15df29c83cfa0c8ade969a14b779e38d695e27",
|
||||
".modelhub_state/official_capabilities.json": "e1669b90f44799ba782b8ca5fc21c65fd00b731437a669a10c7b709f9aafd001",
|
||||
".modelhub_state/outcome_checkpoint.json": "a57a20919bc76a1d0be8c3f4c2daf877151127748e02994284628955d88ae378",
|
||||
".modelhub_state/queue_cleanup_latest.json": "25b335b72d13b2b3ece533c0d2becb501b6af2b8e22541f81dbe2557eefe8d4f",
|
||||
".modelhub_state/recent_outcomes.jsonl": "a6922b033a6620de4c1eebf27e571bc594980df5d0b7d7d7ae8eb909b24661eb",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "4183c2a185cb16ca73111ef73bbdc0e6bbab02005b2a906b0e4ce326929127f0",
|
||||
".modelhub_state/recovery_intents.jsonl": "bb06fa7cfb7fd8d2673b3698d09b7ea31cef26c3e6c8746e7710b4e7b45ddac0",
|
||||
".modelhub_state/recent_outcomes.jsonl": "62b68350d2deff304f19dc514feafd289130899668daa0d9df637ed7ef04be42",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "8cc7f3a1ce9dc3d842b33685ea1bf8f00c684649c442d3d2905691ced8e79e7b",
|
||||
".modelhub_state/recovery_intents.jsonl": "28c616cccafa47a4a6cf69d4e22eb1da36d96ea36d9af745c21b067ea4ff8e59",
|
||||
".modelhub_state/routing_intelligence.json": "883bf953aeb66decf6d3562b5f6db7e61496d89258dbd29ffbedda006925e315",
|
||||
".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7",
|
||||
".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23",
|
||||
"ledger/submissions.jsonl": "a3739d0bad6c76e38f92b3c7ebf51fb5487bd4bed12dc5016005aece1823688c",
|
||||
"outcomes/submissions.jsonl": "82b169076ee6683311d72a05da2becf4c32f9bac6494022b377e5dc35746407f"
|
||||
},
|
||||
"generation": 10296,
|
||||
"generation": 10297,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-20T05:58:18.239058+00:00",
|
||||
"updatedAt": "2026-09-20T05:59:29.031588+00:00",
|
||||
"writerId": "fc715c06e24c4db2ae3e425e435db996"
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user