diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 824a280f2..f552fe273 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -831,7 +831,7 @@ {"batchId": "fb63e96d7b8a40528b70e163893b2424", "completedAt": "2026-09-16T13:48:59.931307+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-16T13:48:52.753438+00:00", "framework": "vllm", "intentId": "33fb044e5ebb46b79509f07277c47b53", "lastModified": "2026-09-14T05:44:50+00:00", "modelAddress": "https://modelscope.cn/models/Edge0/Edge0-8B-A1B-preview", "reason": null, "reconciledAt": "2026-09-16T15:01:14.535861+00:00", "repoId": "Edge0/Edge0-8B-A1B-preview", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4893637", "taskType": "text-generation"} {"batchId": "5e9c2c23281145c7a7647d519161fdfb", "completedAt": "2026-09-16T13:58:01.695403+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-16T13:57:52.380233+00:00", "framework": "vllm", "intentId": "f6b6a2202a2b4df0bfbfac9f8afdce50", "lastModified": "2026-09-16T13:23:00+00:00", "modelAddress": "https://modelscope.cn/models/ManniX-ITA/Ornith-1.5-27B-A3B-CoderX", "reason": null, "reconciledAt": "2026-09-16T15:01:14.537192+00:00", "repoId": "ManniX-ITA/Ornith-1.5-27B-A3B-CoderX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4893794", "taskType": "text-generation"} {"batchId": "618d59fd9fd0475fa50c4e9b31480986", "completedAt": "2026-09-16T14:34:23.707852+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-16T14:34:10.680067+00:00", "framework": "vllm-patch-tokenizer", "intentId": "2b3d2a230ef54358ae9f419b46bbbfe8", "lastModified": "2026-09-16T13:23:00+00:00", "modelAddress": "https://modelscope.cn/models/ManniX-ITA/Ornith-1.5-27B-A3B-CoderX", "reason": null, "reconciledAt": "2026-09-16T15:01:14.537428+00:00", "repoId": "ManniX-ITA/Ornith-1.5-27B-A3B-CoderX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "4894604", "taskType": "text-generation"} -{"batchId": "7b330486838e4769aff5e509725a0cfd", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-16T15:04:27.496435+00:00", "framework": "vllm_tokenizer_patch", "intentId": "624427da2abe4b35a3360da51db702d6", "lastModified": "2026-08-20T03:16:06+00:00", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-MLX-6bit", "repoId": "ornith-ai/Ornith-1.5-9B-MLX-6bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "7b330486838e4769aff5e509725a0cfd", "completedAt": "2026-09-16T15:04:41.245841+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-16T15:04:27.496435+00:00", "framework": "vllm_tokenizer_patch", "intentId": "624427da2abe4b35a3360da51db702d6", "lastModified": "2026-08-20T03:16:06+00:00", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-MLX-6bit", "reason": null, "repoId": "ornith-ai/Ornith-1.5-9B-MLX-6bit", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4895729", "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"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index d91ee61e8..9dbabbfb6 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,13 +1,13 @@ { "acceptedByCategory": { - "unified_success_first": 966 + "unified_success_first": 967 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 13, "text-generation|Ascend_910-b3|vllm": 16, "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 38, "text-generation|Ascend_910-b4|llamacpp": 9, - "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 41, + "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 42, "text-generation|Biren_166m|vllm": 56, "text-generation|Biren_166m|vllm_fix_tokenizer": 6, "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 39, @@ -27,8 +27,8 @@ "text-generation|hygon_k100-ai|llamacpp": 13, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 57 }, - "acceptedSinceRefresh": 966, - "acceptedTotal": 966, - "generatedAt": "2026-09-16T14:34:23.665449+00:00", + "acceptedSinceRefresh": 967, + "acceptedTotal": 967, + "generatedAt": "2026-09-16T15:04:41.196262+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index c2f33e5b3..3b08830d2 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -797,3 +797,4 @@ {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "submitTime": "2026-09-09T21:08:22.097030+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746441", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/XYZ-Aquila-mini-OptiQ-4bit", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit", "submitTime": "2026-09-15T04:40:55.440325+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4866579", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "submitTime": "2026-09-15T04:40:55.438125+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4866581", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-MLX-6bit", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-6bit", "submitTime": "2026-09-16T15:04:28.222294+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4895729", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"} diff --git a/manifest.json b/manifest.json index a62870eb5..dfd7a0388 100644 --- a/manifest.json +++ b/manifest.json @@ -9,16 +9,16 @@ ".modelhub_state/queue_cleanup_latest.json": "057079282bc277b3a97c1805915c45464c12312f8ee3ba54d0366d05f34f4466", ".modelhub_state/recent_outcomes.jsonl": "f13c8a5624d8090382f698e92471a1e8e88db1c57f5e9f580d3403eee853f0d3", ".modelhub_state/recovery_active_tasks.jsonl": "c5cad74aec4ee61f3e33971f84514be4163b6d27ea8bfc4cbd07721b6dbe41ff", - ".modelhub_state/recovery_intents.jsonl": "0d36f7fe839de7497d833a46cb63bf66cce8ce2871b1207ed2e57ccd798aebe1", - ".modelhub_state/routing_intelligence.json": "7a87ac8a69c63d66357fedcedd96ebe3f49d31ba3e254a40889176b9d619986e", + ".modelhub_state/recovery_intents.jsonl": "82503ccb2a39d9c17fc6f266393809dc1e56d7240d802d9b6c768dfe790d2b99", + ".modelhub_state/routing_intelligence.json": "5457822255a1d44bc637c0fd0f4d48930bcbf88824ed76de1db7f925d68d277f", ".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552", ".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983", - "ledger/submissions.jsonl": "17d66e6df14be3e698d9abd0a6c358e3161c7e30c10474e9029730d38c8ee10d", - "outcomes/submissions.jsonl": "02670942e941835885a3e490b770245607e860a8a71c25af338f3a0dceb18f8b" + "ledger/submissions.jsonl": "d781a984d9056b911eb398e8ea24a238e8a1264f2646c276dce87b4f20b84279", + "outcomes/submissions.jsonl": "9c61a81055fa9c6e34bcd7402a80285aa0537a4310fc854d81388268bc16850b" }, - "generation": 8242, - "phase": "intent", + "generation": 8243, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-16T15:04:27.610027+00:00", + "updatedAt": "2026-09-16T15:04:41.347120+00:00", "writerId": "eccb3e0018f640d19e578c271a207b5c" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 5b3c9a995..f91c9f4b5 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -637,3 +637,4 @@ {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "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": "2026-09-16T13:48:53.545119+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4893637", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "ManniX-ITA/Ornith-1.5-27B-A3B-CoderX", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 52429250296, "estimatedRequiredGiB": 58.623, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe_text", "modelscopeFileSize": 52454809630, "modelscopeLicense": "apache-2.0", "modelscopeParams": 26213016704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:expert-pruning", "custom_tag:code", "custom_tag:mtp", "custom_tag:ornith", "custom_tag:reap", "custom_tag:ream", "custom_tag:omnimergekit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 52454809833}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-16T13:57:53.213845+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4893794", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "ManniX-ITA/Ornith-1.5-27B-A3B-CoderX", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 52429250296, "estimatedRequiredGiB": 58.623, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe_text", "modelscopeFileSize": 52454809630, "modelscopeLicense": "apache-2.0", "modelscopeParams": 26213016704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:expert-pruning", "custom_tag:code", "custom_tag:mtp", "custom_tag:ornith", "custom_tag:reap", "custom_tag:ream", "custom_tag:omnimergekit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 52454809833}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-16T14:34:11.624213+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4894604", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "ornith-ai/Ornith-1.5-9B-MLX-6bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7276346365, "estimatedRequiredGiB": 8.156, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 7298158256, "modelscopeLicense": null, "modelscopeParams": 1959473664, "modelscopeTags": ["model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7298158256}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-16T15:04:28.222294+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4895729", "taskType": "text-generation", "verifyResult": null}