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

state: generation 6120 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-12 08:49:44 +00:00
parent 2f386a8522
commit 2d90305b6d
9 changed files with 2049 additions and 2054 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -222,7 +222,7 @@
"ascend_910-b4|vllm|text-generation|model_type:qwen3_5": {
"architectureSignature": "model_type:qwen3_5",
"architectures": [],
"evidenceCount": 2,
"evidenceCount": 1,
"expiresAt": "2026-10-09T15:33:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-09T15:33:21+00:00",
@@ -230,12 +230,10 @@
"matchType": "model_type",
"modelType": "qwen3_5",
"sourceModelIds": [
"mlx-community/Ornith-1.0-9B-4bit",
"cyankiwi/Ornith-1.0-9B-AWQ-FP8"
"mlx-community/Ornith-1.0-9B-4bit"
],
"sourceTaskIds": [
"4079339",
"4079094"
"4079339"
],
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation"
@@ -1364,7 +1362,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-12T08:46:43.923798+00:00",
"generatedAt": "2026-09-12T08:49:43.712022+00:00",
"summary": {
"activeBlockCount": 69,
"byGpuFramework": {

6
.modelhub_state/architecture_history_backfill.json
View File

@@ -35,7 +35,7 @@
"2": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 440,
"listingErrors": 441,
"nextPage": 1,
"recordsScanned": 0,
"uniqueRecords": 0
@@ -102,12 +102,12 @@
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
"failureLogsInspected": 0,
"mode": "incremental_decision_only",
"nextAccountIndex": 2,
"nextAccountIndex": 3,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-12T08:46:43.897695+00:00",
"updatedAt": "2026-09-12T08:49:43.681757+00:00",
"version": 1
}

2
.modelhub_state/market_intelligence.json
View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-12T08:44:52.417040+00:00",
"generatedAt": "2026-09-12T08:47:52.073308+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

1506
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

94
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-12T08:38:57.450801+00:00",
"lastSyncTime": "2026-09-12T08:38:57.213433+00:00",
"generatedAt": "2026-09-12T08:47:45.080978+00:00",
"lastSyncTime": "2026-09-12T08:47:44.834299+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -226,7 +226,7 @@
"ascend_910-b4|vllm|text-generation|model_type:qwen3_5": {
"architectureSignature": "model_type:qwen3_5",
"architectures": [],
"evidenceCount": 2,
"evidenceCount": 1,
"expiresAt": "2026-10-09T15:33:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-09T15:33:21+00:00",
@@ -234,12 +234,10 @@
"matchType": "model_type",
"modelType": "qwen3_5",
"sourceModelIds": [
"mlx-community/Ornith-1.0-9B-4bit",
"cyankiwi/Ornith-1.0-9B-AWQ-FP8"
"mlx-community/Ornith-1.0-9B-4bit"
],
"sourceTaskIds": [
"4079339",
"4079094"
"4079339"
],
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation"
@@ -1845,30 +1843,30 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 89,
"decisionFailureRate": 0.8725,
"decisionSuccessRate": 0.1275,
"decisionTotal": 102,
"attributableFailureCount": 90,
"decisionFailureRate": 0.8738,
"decisionSuccessRate": 0.1262,
"decisionTotal": 103,
"failureBreakdown": {
"ambiguous_runtime": 19,
"framework_architecture_unsupported": 49,
"memory_capacity": 1,
"model_load": 39,
"model_load": 40,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 158,
"failureRate": 0.924,
"failureCount": 159,
"failureRate": 0.9244,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 13,
"successRate": 0.076,
"successRate": 0.0756,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 171,
"total": 172,
"unresolvedFailureCount": 68
},
"Iluvatar_mrv-100|vllm|text-generation": {
@@ -2370,29 +2368,29 @@
"unresolvedFailureCount": 7
},
"unknown": {
"attributableFailureCount": 144,
"decisionFailureRate": 0.7347,
"decisionSuccessRate": 0.2653,
"decisionTotal": 196,
"attributableFailureCount": 145,
"decisionFailureRate": 0.736,
"decisionSuccessRate": 0.264,
"decisionTotal": 197,
"failureBreakdown": {
"ambiguous_runtime": 131,
"backend_operator": 4,
"framework_architecture_unsupported": 91,
"memory_capacity": 5,
"model_load": 41,
"model_load": 42,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3,
"参数/模板问题": 59,
"验证失败": 673
},
"failureCount": 1008,
"failureRate": 0.9509,
"failureCount": 1009,
"failureRate": 0.951,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 52,
"successRate": 0.0491,
"total": 1060,
"successRate": 0.049,
"total": 1061,
"unresolvedFailureCount": 863
},
"vllm": {
@@ -2524,7 +2522,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T08:38:57.446440+00:00",
"generatedAt": "2026-09-12T08:47:45.070626+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2688,27 +2686,27 @@
"unresolvedFailureCount": 44
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 90,
"decisionFailureRate": 0.8738,
"decisionSuccessRate": 0.1262,
"decisionTotal": 103,
"attributableFailureCount": 91,
"decisionFailureRate": 0.875,
"decisionSuccessRate": 0.125,
"decisionTotal": 104,
"failureBreakdown": {
"ambiguous_runtime": 19,
"framework_architecture_unsupported": 49,
"memory_capacity": 1,
"model_load": 40,
"model_load": 41,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 159,
"failureRate": 0.9244,
"failureCount": 160,
"failureRate": 0.9249,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 13,
"successRate": 0.0756,
"total": 172,
"successRate": 0.0751,
"total": 173,
"unresolvedFailureCount": 68
},
"Kunlunxin_p-800": {
@@ -4464,7 +4462,7 @@
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 15,
"consecutiveFailures": 1,
"consecutiveFailures": 2,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8333,
"decisionSuccessRate": 0.1667,
@@ -4478,7 +4476,7 @@
"failureRate": 0.85,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T08:38:57.213433+00:00",
"lastTerminalAt": "2026-09-12T08:47:44.834299+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -7185,19 +7183,19 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1705,
"totalRecords": 1792,
"terminalRecords": 1706,
"totalRecords": 1793,
"totals": {
"attributableFailureCount": 471,
"decisionFailureRate": 0.892,
"decisionSuccessRate": 0.108,
"decisionTotal": 528,
"attributableFailureCount": 472,
"decisionFailureRate": 0.8922,
"decisionSuccessRate": 0.1078,
"decisionTotal": 529,
"failureBreakdown": {
"ambiguous_runtime": 399,
"backend_operator": 42,
"framework_architecture_unsupported": 288,
"memory_capacity": 11,
"model_load": 69,
"model_load": 70,
"platform_infrastructure": 4,
"repository_structure": 7,
"runtime_memory": 6,
@@ -7205,21 +7203,20 @@
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1648,
"failureCount": 1649,
"failureRate": 0.9666,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 57,
"successRate": 0.0334,
"total": 1705,
"total": 1706,
"unresolvedFailureCount": 1173
},
"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。",
@@ -7228,6 +7225,7 @@
"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。",
@@ -7249,6 +7247,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1792,
"summarizedRecords": 1793,
"version": 1
}

2
.modelhub_state/recent_outcomes.jsonl
View File

@@ -1,3 +1,4 @@
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-12T08:47:44.834299+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T08:41:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523323", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-12T08:38:57.213433+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T08:35:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523313", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-12T08:20:40.114700+00:00", "modelId": "RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-12T08:17:22+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523325", "taskType": "text-generation", "verifyResult": 1}
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T08:20:40.114654+00:00", "modelId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T08:13:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4547659", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"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": ["mellum"], "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-08T18:32:01.542091+00:00", "modelId": "JetBrains/Mellum2-12B-A2.5B-Thinking-SFT", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T18:27:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4152885", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-08T18:12:11.499754+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T18:05:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4460344", "taskType": "text-generation", "verifyResult": -1}
{"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": "2026-09-08T18:12:11.499780+00:00", "modelId": "ModelCloud.AI/Qwen2.5-0.5B-Instruct-gptqmodel-4bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T18:03:22+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079264", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-08T18:01:26.308083+00:00", "modelId": "cyankiwi/Ornith-1.0-9B-AWQ-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T17:59:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079094", "taskType": "text-generation", "verifyResult": -1}

1211
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

1252
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff

20
manifest.json
View File

@@ -1,24 +1,24 @@
{
"agentVersion": "2026.09.04.4",
"checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "2ae22c9482d6b45ba753a390ebac7863190f88df82ec0bfdd688a6a535f15434",
".modelhub_state/architecture_history_backfill.json": "e9c1ad0d5277b05bd48f7d3985959dc8159aae7840636e9881ab23e98db720cb",
".modelhub_state/market_intelligence.json": "f799a142ed6bac901812d121d2b1ecd7e2a0df050607572502f63972b63994e5",
".modelhub_state/official_capabilities.json": "e5f2852e98b0b948ef4909606ff68b8cf7c23257fdd0a82dc9341bcef72aa6b2",
".modelhub_state/outcome_checkpoint.json": "0301d9b6ae8c111fa305d5cd714b6aa24d7d328685b2ddcfcca91f1138936b92",
".modelhub_state/architecture_compatibility_blacklist.json": "2bc44c1ba4140203927a4a0d4d92fb9d419d96e59ca2ee8de0a00758c5946fb1",
".modelhub_state/architecture_history_backfill.json": "c3b8822393e0a60c00fb896aa050f3cf9421e0663c7b36b110e461f3d174ee22",
".modelhub_state/market_intelligence.json": "a3597905e602b1a069436750965c7a27edfd1f8facd1e530e3dabd9bfa935e09",
".modelhub_state/official_capabilities.json": "3963e960cc4cfaa811fa9116539b7d260325fe567a10d54ef855065a4cf4f41b",
".modelhub_state/outcome_checkpoint.json": "1cbfc54d6807200122a231e694e59059486319702b7ce72f8fd2155b569e1415",
".modelhub_state/queue_cleanup_latest.json": "6b05059de615759adb561da08f7e955c6aa7fc0a1781227efab19cf90b539800",
".modelhub_state/recent_outcomes.jsonl": "0180d194ddedf10c4e9724a8ad99d82e6854367871f30372bd8bb2b2e95a1aeb",
".modelhub_state/recovery_active_tasks.jsonl": "08ceefbde337e52cf68e3aec282b1294853f8fda41683fe0f78ddee27bf11eca",
".modelhub_state/recovery_intents.jsonl": "367d7710a43d0c4a739a7064cd3086a44d24e243ba34f50b6aa9f79ec7871a43",
".modelhub_state/recent_outcomes.jsonl": "f3142235f4c2aff3032775656a21b179bb82c53a4f701266dcd41c7675d4301f",
".modelhub_state/recovery_active_tasks.jsonl": "6481f8f799c3b83c28dae5595c7367f6694073bbd47ea15153a9a54372355a57",
".modelhub_state/recovery_intents.jsonl": "28e5868aa1ae868de6ccb5e03e48c54be8d3f73f68d3eb0dae2d842f9a846d97",
".modelhub_state/routing_intelligence.json": "2855b5a64db2097d238c63bc8e3c9527429b37e5743e8c4067b04a47b96bf6d5",
".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220",
".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162",
"ledger/submissions.jsonl": "fce27fb2f360720694402834960f8bd72b07cc9cdb7df41af2ff877c48deb61a",
"outcomes/submissions.jsonl": "c1fb4ffb5f8805609635341d14f8a0d312d7065898c795a6d23cb2b73c0d9814"
},
"generation": 6119,
"generation": 6120,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-12T08:46:44.024098+00:00",
"updatedAt": "2026-09-12T08:49:44.344796+00:00",
"writerId": "e5dd59a4c84a4f21926bad61448789e2"
}