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

state: generation 8321 (intent)

Browse Source
This commit is contained in:
CoolBoy
2026-09-16 17:52:32 +00:00
parent b044bf13d1
commit 38f0de98c6
7 changed files with 815 additions and 814 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -1695,7 +1695,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-16T17:49:40.733375+00:00",
"generatedAt": "2026-09-16T17:50:43.322728+00:00",
"summary": {
"activeBlockCount": 82,
"byGpuFramework": {

2
.modelhub_state/market_intelligence.json
View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-16T17:47:44.602421+00:00",
"generatedAt": "2026-09-16T17:50:56.864310+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

1535
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

68
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-16T17:09:11.469983+00:00",
"lastSyncTime": "2026-09-16T17:09:11.209777+00:00",
"generatedAt": "2026-09-16T17:50:43.287506+00:00",
"lastSyncTime": "2026-09-16T17:50:41.534349+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2327,10 +2327,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 50,
"ambiguous_runtime": 51,
"参数/模板问题": 2
},
"failureCount": 52,
"failureCount": 53,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -2340,8 +2340,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 52,
"unresolvedFailureCount": 52
"total": 53,
"unresolvedFailureCount": 53
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2882,7 +2882,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 57,
"failureBreakdown": {
"ambiguous_runtime": 53,
"ambiguous_runtime": 54,
"backend_operator": 2,
"framework_architecture_unsupported": 9,
"model_load": 1,
@@ -2890,15 +2890,15 @@
"tokenizer_compatibility": 45,
"参数/模板问题": 8
},
"failureCount": 125,
"failureCount": 126,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 7,
"successCount": 0,
"successRate": 0.0,
"total": 125,
"unresolvedFailureCount": 61
"total": 126,
"unresolvedFailureCount": 62
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 6,
@@ -2920,7 +2920,7 @@
"unresolvedFailureCount": 5
}
},
"generatedAt": "2026-09-16T17:09:11.465074+00:00",
"generatedAt": "2026-09-16T17:50:43.281863+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 49,
@@ -3116,20 +3116,20 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 95,
"ambiguous_runtime": 96,
"memory_capacity": 1,
"参数/模板问题": 2,
"验证失败": 23
},
"failureCount": 121,
"failureCount": 122,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 121,
"unresolvedFailureCount": 120
"total": 122,
"unresolvedFailureCount": 121
},
"MetaX_c-500": {
"attributableFailureCount": 58,
@@ -4934,10 +4934,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 4,
"ambiguous_runtime": 5,
"参数/模板问题": 1
},
"failureCount": 5,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5",
@@ -4949,8 +4949,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 5
"total": 6,
"unresolvedFailureCount": 6
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3|none": {
"attributableFailureCount": 0,
@@ -9233,10 +9233,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2,
"ambiguous_runtime": 3,
"参数/模板问题": 1
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 34,
@@ -9249,8 +9249,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 4,
"unresolvedFailureCount": 4
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3|none|24": {
"attributableFailureCount": 0,
@@ -10993,15 +10993,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2033,
"totalRecords": 2127,
"terminalRecords": 2034,
"totalRecords": 2128,
"totals": {
"attributableFailureCount": 654,
"decisionFailureRate": 0.8922,
"decisionSuccessRate": 0.1078,
"decisionTotal": 733,
"failureBreakdown": {
"ambiguous_runtime": 493,
"ambiguous_runtime": 494,
"backend_operator": 45,
"framework_architecture_unsupported": 429,
"memory_capacity": 12,
@@ -11013,29 +11013,29 @@
"参数/模板问题": 124,
"验证失败": 673
},
"failureCount": 1954,
"failureRate": 0.9611,
"failureCount": 1955,
"failureRate": 0.9612,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 10,
"successCount": 79,
"successRate": 0.0389,
"total": 2033,
"unresolvedFailureCount": 1290
"successRate": 0.0388,
"total": 2034,
"unresolvedFailureCount": 1291
},
"warnings": [
"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 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-x8 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 hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU MetaX_c-500 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 Ascend_910-b3 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 Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
"组合 Biren_166m|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 Biren_166m|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_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -11060,6 +11060,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2127,
"summarizedRecords": 2128,
"version": 1
}

1
.modelhub_state/recovery_intents.jsonl
View File

@@ -842,6 +842,7 @@
{"batchId": "eb5c543e0afe4add9645387528a54f8a", "completedAt": "2026-09-16T17:33:53.499007+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-16T17:33:44.372098+00:00", "framework": "vllm_tokenizer_patch", "intentId": "513aeb75b6fa4a98ae975942dc1099be", "lastModified": "2026-08-31T03:14:07+00:00", "modelAddress": "https://modelscope.cn/models/rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "reason": null, "reconciledAt": "2026-09-16T17:43:29.334947+00:00", "repoId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "4899710", "taskType": "text-generation"}
{"batchId": "704c196b3cea458792ffa8f127971369", "completedAt": "2026-09-16T17:39:10.211685+00:00", "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configSource": "modelhub_live", "createdAt": "2026-09-16T17:39:00.731190+00:00", "framework": "vllm", "intentId": "46ad10964f9e4fc2a69816736af0797a", "lastModified": "2026-09-16T16:05:58+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/RoboBrain2.5-8B-NV", "reason": null, "reconciledAt": "2026-09-16T17:43:29.333922+00:00", "repoId": "BAAI/RoboBrain2.5-8B-NV", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "4899818", "taskType": "text-generation"}
{"batchId": "704c196b3cea458792ffa8f127971369", "completedAt": "2026-09-16T17:39:10.211697+00:00", "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configSource": "modelhub_live", "createdAt": "2026-09-16T17:39:00.731291+00:00", "framework": "vllm", "intentId": "c57d4161935d4f00804ebdc5c279036d", "lastModified": "2026-09-16T13:23:00+00:00", "modelAddress": "https://modelscope.cn/models/ManniX-ITA/Ornith-1.5-27B-A3B-CoderX", "reason": null, "reconciledAt": "2026-09-16T17:43:29.334361+00:00", "repoId": "ManniX-ITA/Ornith-1.5-27B-A3B-CoderX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "4899817", "taskType": "text-generation"}
{"batchId": "80baa6bec20540a887287c2ff05db08d", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-16T17:52:32.309040+00:00", "framework": "vllm", "intentId": "969082ac07ee4c23a6e8cc2a52e5348e", "lastModified": "2026-08-31T03:14:07+00:00", "modelAddress": "https://modelscope.cn/models/rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "repoId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation"}
{"batchId": "83639d5151dd4bb78879458f9850c53a", "completedAt": "2026-09-14T06:07:56.622377+00:00", "configFingerprint": "e4588bdbccc377f0f7599581ea0752e64b81eda54f82b575b6aaa81c27ce2e73", "configSource": "modelhub_live", "createdAt": "2026-09-14T06:07:48.751836+00:00", "framework": "llamacpp", "intentId": "35fd7d8028f54640b4d005111704edc0", "repoId": "voconly/nemotron-3.5-asr-streaming-0.6b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "9ea43510e22a43e9991959f19dd0f4a2", "completedAt": "2026-09-13T12:43:37.101071+00:00", "configFingerprint": "7d273c6d9a11c4e826d64fc44d3ae14d805bd3b1e6e663d4dd0b45567cfc5e3f", "configSource": "modelhub_live", "createdAt": "2026-09-13T12:43:27.207464+00:00", "framework": "llamacpp", "intentId": "ab083753c716462fbb8b0529ac182658", "repoId": "voconly/nemotron-3.5-asr-streaming-0.6b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "uniqueness_rejected", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
{"batchId": "9370c3290d2242cebbdd1924870f426b", "completedAt": "2026-09-13T12:41:31.618354+00:00", "configFingerprint": "d7cf4e4fcae21f022bbcb9f71b3bb0ab37d6331cf8fd1cd3ad4ba75043690051", "configSource": "modelhub_live", "createdAt": "2026-09-13T12:41:17.857077+00:00", "framework": "llamacpp", "intentId": "8c62b06728694cd9b6f7c5c378f53285", "repoId": "voconly/nemotron-3.5-asr-streaming-0.6b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}

18
manifest.json
View File

@@ -1,24 +1,24 @@
{
"agentVersion": "2026.09.04.4",
"checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "afa25ec157a473ccf898b599136937f1a7293036033310eb3a4bcbc73d5dd989",
".modelhub_state/architecture_compatibility_blacklist.json": "5a518d35c78577af592975879d38cd1f894a8aa2edeb038c26a4a6995e0733de",
".modelhub_state/architecture_history_backfill.json": "b35a4b8b92f269af7cf9c7d5b06d8daf279165d2296f36f6007b943acac0e69b",
".modelhub_state/market_intelligence.json": "82ed1d7923948419c723c5d40dea24ec784ff15be162ccf3dc5374d5dc22107b",
".modelhub_state/official_capabilities.json": "8da83c74fb68a549a9abf2353724379a835c15cf0d318d6d2e19acbba32c26e2",
".modelhub_state/outcome_checkpoint.json": "43c4e41958121aaaa4be1068a257e7708aad644d00b9a9a3852ef2c99c1d6635",
".modelhub_state/market_intelligence.json": "43a20542a76cf02857084766ccc5edc8b8bff41fb781001282ac1efe068d0d83",
".modelhub_state/official_capabilities.json": "25483c1f58577361dce30b206e3e4f273fd41a86cda8bcbd213b911f059cb606",
".modelhub_state/outcome_checkpoint.json": "3afc57df3677451850f1439a8d5d9784816e15a46ac48f88dfbf67eb0adfbb24",
".modelhub_state/queue_cleanup_latest.json": "057079282bc277b3a97c1805915c45464c12312f8ee3ba54d0366d05f34f4466",
".modelhub_state/recent_outcomes.jsonl": "4647f63c856ce0f5a014c36cc12aa304266c858bf6c218b953ef85e3c811ce8e",
".modelhub_state/recovery_active_tasks.jsonl": "f34ffd07b3c962cca200080718429f6fad9a9a081ac6efeb6f2512e3f88d2a08",
".modelhub_state/recovery_intents.jsonl": "1d9ab0a68a4b156217cd1fc4c96d18917f695066f7541a216bf22730c0229291",
".modelhub_state/recovery_intents.jsonl": "3b193971c6143a003a09a90313af9e89106c576666981d7becd717cc7cf3d1a5",
".modelhub_state/routing_intelligence.json": "b5d5836677350ec2c350cf6a0f6cd9756d0fe180f31310874a898bd324486828",
".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552",
".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983",
"ledger/submissions.jsonl": "caab6e48dab67829d800849dd0fc7130978b30c08e1db6d662e93c01ab7ad70b",
"outcomes/submissions.jsonl": "0e943c682c2d24678b8539f74a2f7d8d0a77c47a50b593745b231c0b746fc438"
"outcomes/submissions.jsonl": "fa6522cb3bfbb7825c5b5009aa4886317b94f66cc87bb9e9e07a7d8e1f317868"
},
"generation": 8320,
"phase": "cycle",
"generation": 8321,
"phase": "intent",
"schemaVersion": 1,
"updatedAt": "2026-09-16T17:49:40.853322+00:00",
"updatedAt": "2026-09-16T17:52:32.396719+00:00",
"writerId": "eccb3e0018f640d19e578c271a207b5c"
}

3
outcomes/submissions.jsonl
View File

@@ -266,7 +266,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504496+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8842796317, "modelscopeLicense": "mit", "modelscopeParams": 6728625904, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 8842796317}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:51.831733+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729515", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504528+00:00", "modelId": "siliconflow/Hunyuan-A13B-Instruct-SF-FP8", "modelProfile": {"architectures": ["HunYuanMoEV1ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1700, "estimatedRequiredGiB": 90.469, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hunyuan", "modelscopeFileSize": 80949912827, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 80393195968, "modelscopeTags": ["license:Apache License 2.0", "model_type:hunyuan", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 80949912827}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:51.924564+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729534", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504596+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426230291, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426230291}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:52.094406+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729529", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504631+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306310880, "estimatedRequiredGiB": 21.599, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19326449341, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9653104368, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:transformers", "custom_tag:unsloth", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:distillation", "custom_tag:deepseek", "custom_tag:sft", "custom_tag:rl", "custom_tag:gspo", "custom_tag:math", "custom_tag:stem", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:mtp"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19326449341}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:52.086476+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729527", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504584+00:00", "modelId": "dealignai/MiniMax-M2.7-JANGTQ-CRACK", "modelProfile": {"architectures": ["MiniMaxM2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 60691028969, "estimatedRequiredGiB": 67.863, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minimax_m2", "modelscopeFileSize": 60722546540, "modelscopeLicense": null, "modelscopeParams": 15303654400, "modelscopeTags": ["model_type:minimax_m2", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:jang", "custom_tag:jangtq", "custom_tag:turboquant", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:apple-silicon", "custom_tag:mlx", "custom_tag:moe", "custom_tag:abliterated", "custom_tag:uncensored", "custom_tag:crack", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 60722546540}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:52.031559+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729530", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504536+00:00", "modelId": "mlx-community/Hy3-OptiQ-2bit", "modelProfile": {"architectures": ["HYV3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 88126421229, "estimatedRequiredGiB": 98.5, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hy_v3", "modelscopeFileSize": 88136486889, "modelscopeLicense": "apache-2.0", "modelscopeParams": 24386771776, "modelscopeTags": ["license:apache-2.0", "model_type:hy_v3", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:quantized", "custom_tag:2bit", "custom_tag:mixed-precision", "custom_tag:moe", "custom_tag:ssd-streaming", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 88136486889}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:52.159484+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729532", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504481+00:00", "modelId": "hf/OBLITERATUS-Ornith-1.5-9B-OBLITERATED", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306303864, "estimatedRequiredGiB": 92.13, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 82436368524, "modelscopeLicense": "mit", "modelscopeParams": 9653104368, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:gguf", "library:safetensors", "task:text-generation", "custom_tag:abliterated", "custom_tag:uncensored", "custom_tag:ornith", "custom_tag:qwen3.5", "custom_tag:obliteratus", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 82436368524}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:52.350274+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729535", "taskType": "text-generation", "verifyResult": null}
@@ -623,7 +622,7 @@
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-16T17:09:11.209752+00:00", "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4563913288, "estimatedRequiredGiB": 5.138, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4597698253, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1268239776, "modelscopeTags": ["license:apache-2.0", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4597698253}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T09:03:09.666793+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4889677", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-16T17:25:59.446149+00:00", "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4563913288, "estimatedRequiredGiB": 5.138, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4597698253, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1268239776, "modelscopeTags": ["license:apache-2.0", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4597698253}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T09:20:28.174669+00:00", "targetGpu": "MetaX_c-500", "taskId": "4889839", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-16T17:41:50.112754+00:00", "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4563913288, "estimatedRequiredGiB": 5.138, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4597698253, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1268239776, "modelscopeTags": ["license:apache-2.0", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4597698253}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T09:37:59.405066+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4890080", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": null, "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4563913288, "estimatedRequiredGiB": 5.138, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4597698253, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1268239776, "modelscopeTags": ["license:apache-2.0", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4597698253}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-16T09:49:03.662873+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4890217", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-16T17:50:41.534321+00:00", "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4563913288, "estimatedRequiredGiB": 5.138, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4597698253, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1268239776, "modelscopeTags": ["license:apache-2.0", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4597698253}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T09:49:03.662873+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4890217", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4563913288, "estimatedRequiredGiB": 5.138, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4597698253, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1268239776, "modelscopeTags": ["license:apache-2.0", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4597698253}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-16T09:59:53.000301+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4890315", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4563913288, "estimatedRequiredGiB": 5.138, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4597698253, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1268239776, "modelscopeTags": ["license:apache-2.0", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4597698253}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-16T10:17:32.995862+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4890520", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4563913288, "estimatedRequiredGiB": 5.138, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4597698253, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1268239776, "modelscopeTags": ["license:apache-2.0", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4597698253}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-16T12:59:29.226923+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4892870", "taskType": "text-generation", "verifyResult": null}