diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 5b53d9f0b5..f685d88536 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -943,7 +943,7 @@ {"batchId": "4cc812b7f6074338b0c6ed46bdd2672b", "completedAt": "2026-09-19T04:58:26.492783+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-19T04:58:15.480445+00:00", "framework": "vllm", "intentId": "eedd6e486a024165b3618afcd74ed344", "lastModified": "2026-08-25T14:08:37+00:00", "modelAddress": "https://modelscope.cn/models/barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "reason": null, "reconciledAt": "2026-09-19T05:13:29.776013+00:00", "repoId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "4947145", "taskType": "text-generation"} {"batchId": "ab6640b9bdc046c784ef179cc238f69f", "completedAt": "2026-09-19T05:04:01.638937+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-19T05:03:54.324324+00:00", "framework": "vllm_fix_tokenizer", "intentId": "02ea5a1931df4d30aae0e8831a19dca7", "lastModified": "2026-09-18T05:43:55+00:00", "modelAddress": "https://modelscope.cn/models/prism-ml/Ternary-Bonsai-2-27B-mlx-2bit", "reason": null, "reconciledAt": "2026-09-19T05:13:29.776975+00:00", "repoId": "prism-ml/Ternary-Bonsai-2-27B-mlx-2bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "4947298", "taskType": "text-generation"} {"batchId": "ab6640b9bdc046c784ef179cc238f69f", "completedAt": "2026-09-19T05:04:01.638947+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-19T05:03:54.324410+00:00", "framework": "vllm_fix_tokenizer", "intentId": "49cce80fa3034b8eadf07be10cd772ad", "lastModified": "2026-09-16T16:32:52+00:00", "modelAddress": "https://modelscope.cn/models/IFM/K2-Horizon-7B-FP8", "reason": null, "reconciledAt": "2026-09-19T05:13:29.776007+00:00", "repoId": "IFM/K2-Horizon-7B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "4947297", "taskType": "text-generation"} -{"batchId": "21c22ba5375240d3ac7658f771cb69aa", "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configSource": "modelhub_live", "createdAt": "2026-09-19T05:16:58.338944+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "intentId": "6ee35deac6e941f9b68eef42750ec0df", "lastModified": "2026-08-25T14:08:37+00:00", "modelAddress": "https://modelscope.cn/models/barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "repoId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} +{"batchId": "21c22ba5375240d3ac7658f771cb69aa", "completedAt": "2026-09-19T05:17:07.099763+00:00", "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configSource": "modelhub_live", "createdAt": "2026-09-19T05:16:58.338944+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "intentId": "6ee35deac6e941f9b68eef42750ec0df", "lastModified": "2026-08-25T14:08:37+00:00", "modelAddress": "https://modelscope.cn/models/barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "reason": null, "repoId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "4947588", "taskType": "text-generation"} {"batchId": "4cc812b7f6074338b0c6ed46bdd2672b", "completedAt": "2026-09-19T04:58:26.492770+00:00", "configFingerprint": "c240df8c4ef51c3028e28d4dbd670173f9ac1f001d6c73625ec2cdaccb288665", "configSource": "modelhub_live", "createdAt": "2026-09-19T04:58:15.480275+00:00", "framework": "llamacpp", "intentId": "ee86b2205fef40f298072ec892726538", "repoId": "voconly/parakeet-unified-en-0.6b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} {"batchId": "8d27d6d5a99748efbdd97223e640c598", "completedAt": "2026-09-18T14:35:12.136557+00:00", "configFingerprint": "359725c5cf0821e26681bc436dad944747db4ac72a1bf9e70b5f6f8e63a023b4", "configSource": "modelhub_live", "createdAt": "2026-09-18T14:35:06.015304+00:00", "framework": "llamacpp", "intentId": "10303336f4f24e2f98aa86764cc2f0fc", "repoId": "voconly/parakeet-unified-en-0.6b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "uniqueness_rejected", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} {"batchId": "bfd8069a25c5437f87c1eb1f45b313b1", "completedAt": "2026-09-18T14:33:31.434713+00:00", "configFingerprint": "e1276bf11e548198418262ddca64a6c4514301bb26e65ecc7e04f8d8f0442b6b", "configSource": "modelhub_live", "createdAt": "2026-09-18T14:33:23.815503+00:00", "framework": "llamacpp", "intentId": "3c35cff71fae4e2997f1d1fa492cdda8", "repoId": "voconly/parakeet-unified-en-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 4362ba74e8..ff86d01c7c 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 1078 + "unified_success_first": 1079 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 17, @@ -15,7 +15,7 @@ "text-generation|Cambricon_mlu-370-x8|vllm-customized": 10, "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 76, "text-generation|Iluvatar_bi-150|llamacpp": 16, - "text-generation|Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 77, + "text-generation|Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 78, "text-generation|Iluvatar_mrv-100|vllm": 55, "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 122, "text-generation|MetaX_c-500|vllm": 99, @@ -27,8 +27,8 @@ "text-generation|hygon_k100-ai|llamacpp": 17, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 63 }, - "acceptedSinceRefresh": 1078, - "acceptedTotal": 1078, - "generatedAt": "2026-09-19T05:04:01.610565+00:00", + "acceptedSinceRefresh": 1079, + "acceptedTotal": 1079, + "generatedAt": "2026-09-19T05:17:07.068826+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 053e09cd18..b5f56b9227 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -717,3 +717,4 @@ {"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_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "submitTime": "2026-09-19T05:16:59.020007+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4947588", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"} diff --git a/manifest.json b/manifest.json index bc5833b23c..153d844959 100644 --- a/manifest.json +++ b/manifest.json @@ -9,16 +9,16 @@ ".modelhub_state/queue_cleanup_latest.json": "318235d5bbb99386d625410dc4623fcffd5f4e8a91bbee6b01f07b687770db6a", ".modelhub_state/recent_outcomes.jsonl": "2fae2359f00256e76fd8cc884daa5230e899c5fb80cc059aa9b2c78663afbd10", ".modelhub_state/recovery_active_tasks.jsonl": "b290b4f61c29c366c87cc66e61b4d5d86c8a81eec4896244df2150bfc22701e5", - ".modelhub_state/recovery_intents.jsonl": "a3a0707db5275f293c34af3cbfa4a5555d2fa00a3cc3539024d425161403cd5b", - ".modelhub_state/routing_intelligence.json": "c7aa84a85da1ee7cf761a5610b8e52fbc8a39189484ac8922d7c7dab36df9ade", + ".modelhub_state/recovery_intents.jsonl": "628a3332b20aa484d83d21a6124e4b8eeb0327cb10b1587ef1dbd4c2abcb9540", + ".modelhub_state/routing_intelligence.json": "0a8ec53d790ca928d280d80292b5bdd6f335b05fad67e337813e6d905d38d8cf", ".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7", ".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23", - "ledger/submissions.jsonl": "9372af29bd4ca8129e3456870a4100e45248134402378f1ad97fbf820a858f46", - "outcomes/submissions.jsonl": "8f4c0058eeb45b627616332ebf211390f2ba783db6e62974bff2066e2229a7d2" + "ledger/submissions.jsonl": "b498ad284d0637bd71972e38b81fbd2afa5e5353f1fb77d3fb9cfb0f462a046d", + "outcomes/submissions.jsonl": "e97019e18b597114e077c75538470dcfe3329cb5332a74786c7f11f76604d912" }, - "generation": 9655, - "phase": "intent", + "generation": 9656, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-19T05:16:58.414871+00:00", + "updatedAt": "2026-09-19T05:17:07.199733+00:00", "writerId": "b4717c3c30654a5585d5941286742f58" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index c8cbf4b5a0..6f4401ac37 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -538,3 +538,4 @@ {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15155811051, "estimatedRequiredGiB": 16.961, "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", "modelscopeFileSize": 15176196372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4210722304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:reasoning", "custom_tag:opus-distill", "custom_tag:whittle", "custom_tag:expert-pruning", "custom_tag:moe", "custom_tag:router-healing", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15176196372}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-19T04:58:16.179657+00:00", "targetGpu": "Biren_166m", "taskId": "4947145", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "prism-ml/Ternary-Bonsai-2-27B-mlx-2bit", "modelProfile": {"architectures": [], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8595477990, "estimatedRequiredGiB": 9.621, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "prism_hadamard_qwen35", "modelscopeFileSize": 8608734989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2589078768, "modelscopeTags": ["license:apache-2.0", "model_type:prism_hadamard_qwen35", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:ternary", "custom_tag:2-bit", "custom_tag:mlx", "custom_tag:cuda", "custom_tag:metal", "custom_tag:on-device", "custom_tag:hybrid-attention", "custom_tag:prismml", "custom_tag:bonsai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8608734989}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-19T05:03:55.038215+00:00", "targetGpu": "Vastai_va16", "taskId": "4947298", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "IFM/K2-Horizon-7B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11053505536, "estimatedRequiredGiB": 12.378, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11075960403, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8999178240, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11075960403}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-19T05:03:55.039513+00:00", "targetGpu": "Vastai_va16", "taskId": "4947297", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": null, "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15155811051, "estimatedRequiredGiB": 16.961, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 15176196372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4210722304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:reasoning", "custom_tag:opus-distill", "custom_tag:whittle", "custom_tag:expert-pruning", "custom_tag:moe", "custom_tag:router-healing", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15176196372}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-19T05:16:59.020007+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4947588", "taskType": "text-generation", "verifyResult": null}