diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 676e5d3be..8c2c009bf 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -911,7 +911,7 @@ {"batchId": "ad988b76b1184214b429c35f0738bb68", "completedAt": "2026-09-18T13:40:36.634527+00:00", "configFingerprint": "20cb3c39f4c481f4f36a82f56d2790a08d35635571c54154d8414aa034539fdd", "configSource": "modelhub_live", "createdAt": "2026-09-18T13:40:30.776266+00:00", "framework": "llamacpp", "intentId": "ef6f8effca114118aaa2c887ddc61e3a", "lastModified": "2026-09-18T05:30:22+00:00", "modelAddress": "https://modelscope.cn/models/ProCreations/Ternary-Bonsai-2-27B-MTP", "reason": null, "reconciledAt": "2026-09-18T14:53:43.985955+00:00", "repoId": "ProCreations/Ternary-Bonsai-2-27B-MTP", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "4935565", "taskType": "text-generation"} {"batchId": "3426ff6e4bf74779836db20baaa89bfc", "completedAt": "2026-09-18T13:59:51.228252+00:00", "configFingerprint": "ec890c5fa72ce5b6a2dc821183a5c5a4672e35039ad1cfdbb4ec3edd6dfa8870", "configSource": "modelhub_live", "createdAt": "2026-09-18T13:59:44.535606+00:00", "framework": "llamacpp", "intentId": "b08a8178c70949559ae3b2e88ed862e1", "lastModified": "2026-09-18T05:30:22+00:00", "modelAddress": "https://modelscope.cn/models/ProCreations/Ternary-Bonsai-2-27B-MTP", "reason": null, "reconciledAt": "2026-09-18T14:53:43.986539+00:00", "repoId": "ProCreations/Ternary-Bonsai-2-27B-MTP", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "4935796", "taskType": "text-generation"} {"batchId": "1057cde16ff64bd080ab15fe58acfe7a", "completedAt": "2026-09-18T14:49:23.693515+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-18T14:49:14.397523+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1acf0acfd43141b78deaf8b97befb2d8", "lastModified": "2026-09-16T16:32:52+00:00", "modelAddress": "https://modelscope.cn/models/IFM/K2-Horizon-7B-FP8", "reason": null, "reconciledAt": "2026-09-18T14:53:43.985732+00:00", "repoId": "IFM/K2-Horizon-7B-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "4936268", "taskType": "text-generation"} -{"batchId": "604b79b346d24c56a3a5aaac6cbbc7e2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-18T15:02:31.567843+00:00", "framework": "vllm_fix_tokenizer", "intentId": "06368add7bae4d378ca0dae55bb87edd", "lastModified": "2026-09-18T05:43:55+00:00", "modelAddress": "https://modelscope.cn/models/prism-ml/Ternary-Bonsai-2-27B-mlx-2bit", "repoId": "prism-ml/Ternary-Bonsai-2-27B-mlx-2bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "604b79b346d24c56a3a5aaac6cbbc7e2", "completedAt": "2026-09-18T15:02:37.237440+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-18T15:02:31.567843+00:00", "framework": "vllm_fix_tokenizer", "intentId": "06368add7bae4d378ca0dae55bb87edd", "lastModified": "2026-09-18T05:43:55+00:00", "modelAddress": "https://modelscope.cn/models/prism-ml/Ternary-Bonsai-2-27B-mlx-2bit", "reason": null, "repoId": "prism-ml/Ternary-Bonsai-2-27B-mlx-2bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4936404", "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"} {"batchId": "18470fd259dd4f84ad6911206103ac42", "completedAt": "2026-09-18T14:31:05.798368+00:00", "configFingerprint": "680fcdbc0952bbae15ed7a5a114782d3eaa8806d60778df64b3e1a99d41a066b", "configSource": "modelhub_live", "createdAt": "2026-09-18T14:30:53.123908+00:00", "framework": "llamacpp", "intentId": "c7daff34b5a4470ab91e00ee1da68653", "repoId": "voconly/parakeet-unified-en-0.6b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index e260399c0..893eccccd 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 1046 + "unified_success_first": 1047 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 16, @@ -17,7 +17,7 @@ "text-generation|Iluvatar_bi-150|llamacpp": 13, "text-generation|Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 77, "text-generation|Iluvatar_mrv-100|vllm": 53, - "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 120, + "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 121, "text-generation|MetaX_c-500|vllm": 98, "text-generation|Mthreads_s4000|llamacpp": 16, "text-generation|Mthreads_s4000|vllm": 79, @@ -27,8 +27,8 @@ "text-generation|hygon_k100-ai|llamacpp": 16, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 61 }, - "acceptedSinceRefresh": 1046, - "acceptedTotal": 1046, - "generatedAt": "2026-09-18T14:49:23.660691+00:00", + "acceptedSinceRefresh": 1047, + "acceptedTotal": 1047, + "generatedAt": "2026-09-18T15:02:37.207319+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 382280a03..a80fdfa14 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -727,3 +727,4 @@ {"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_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/prism-ml/Ternary-Bonsai-2-27B-mlx-2bit", "modelId": "prism-ml/Ternary-Bonsai-2-27B-mlx-2bit", "submitTime": "2026-09-18T15:02:32.216517+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4936404", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} diff --git a/manifest.json b/manifest.json index 70d80d63d..027e877b0 100644 --- a/manifest.json +++ b/manifest.json @@ -9,16 +9,16 @@ ".modelhub_state/queue_cleanup_latest.json": "3c142558258883a3e45602d09e9392c46bfde3deae83aabc51d01f3b1c2d91d9", ".modelhub_state/recent_outcomes.jsonl": "0fcc5f6784cf629062af94f10b04ccbc582a860e12e784a4d245b58baae2c602", ".modelhub_state/recovery_active_tasks.jsonl": "7db5dfaf9b8322cbba85ab4250dc72a2735d85ac4aa140da83fe19060e9ef31b", - ".modelhub_state/recovery_intents.jsonl": "ceb57b812f1de79870f3d7b3b6d2b11410ff04e9832371af2661eea12366d381", - ".modelhub_state/routing_intelligence.json": "04e8c544598fdfd0ac0d85716ca044be174fef3291383d39cc7ed332e3eec18b", + ".modelhub_state/recovery_intents.jsonl": "298d7c8ab9e98758440d5f3775940f58e9fe9bcf7ec48e434c1f434618d9ef27", + ".modelhub_state/routing_intelligence.json": "f192aecf609c9baa8117fe69c5428efdb8bd6ae1488397de432a175891cad19e", ".modelhub_state/submission_exclusions.jsonl": "cd362b9c480f30eb8106e264359b19b37b894120db54586e63b0a0d1d41a73b0", ".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23", - "ledger/submissions.jsonl": "27a9b572043e061fcc82a5f605114886a714e277a74d4657e4e065ecd541102e", - "outcomes/submissions.jsonl": "416e29af769cd9a429d33fe3d1bbb46653a066ad94980d96fbda3ff7b4426b1c" + "ledger/submissions.jsonl": "389756d415bc0cffda23dbb42b9a410d302cd36a5e3f5613874d149b4fea0255", + "outcomes/submissions.jsonl": "16fa9a8860995e85472af6f18c7468df32a9d8789e3842bfe121b300fbc59087" }, - "generation": 9312, - "phase": "intent", + "generation": 9313, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-18T15:02:31.643242+00:00", + "updatedAt": "2026-09-18T15:02:37.302227+00:00", "writerId": "217f1806b49c401894bed7ce18be9095" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 3635f2e73..e22d31f73 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -544,3 +544,4 @@ {"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "ProCreations/Ternary-Bonsai-2-27B-MTP", "modelProfile": {"architectures": [], "configFingerprint": "20cb3c39f4c481f4f36a82f56d2790a08d35635571c54154d8414aa034539fdd", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7657489728, "estimatedRequiredGiB": 9.567, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 8560440422, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:qwen3_5", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:bonsai", "custom_tag:ternary", "custom_tag:blackwell", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8560440422}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-18T13:40:31.530904+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4935565", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "ProCreations/Ternary-Bonsai-2-27B-MTP", "modelProfile": {"architectures": [], "configFingerprint": "ec890c5fa72ce5b6a2dc821183a5c5a4672e35039ad1cfdbb4ec3edd6dfa8870", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7657489728, "estimatedRequiredGiB": 9.567, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 8560440422, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:qwen3_5", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:bonsai", "custom_tag:ternary", "custom_tag:blackwell", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8560440422}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-18T13:59:45.181269+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4935796", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "IFM/K2-Horizon-7B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "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": "2026-09-18T14:49:15.451907+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4936268", "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": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8595477990, "estimatedRequiredGiB": 9.621, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": "2026-09-18T15:02:32.216517+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4936404", "taskType": "text-generation", "verifyResult": null}