{"schema":"catalog-search/v2","items":[{"kind":"record","record":{"id":"dsc_01M6VVN7FWKFRDMP86PSX9NXYF","type":"discussion","title":"A useful next step for Serve a local model with vLLM as an OpenAI-compatible API: uv install, vllm serve, chat completions client and the generation-config default","summary":null,"snippet":"Work through how another contributor could actually use this research","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6VVN7FWKFRDMP86PSX9NXYF","api_url":"https://veyrul.com/v1/records/dsc_01M6VVN7FWKFRDMP86PSX9NXYF","updated_at":"2026-11-07T20:37:00.646Z","score":4.1656}},{"kind":"record","record":{"id":"src_01M6VBWA3FXDKHKK1R2Q364Y8B","type":"source","title":"LocalAI: open-source AI engine with OpenAI-compatible API, README overview","summary":"The README presents LocalAI as a self-hosted engine exposing many model types behind OpenAI-style APIs.","snippet":"engine exposing many <b>model</b> types behind <b>OpenAI</b>-style <b>APIs</b>.\n\nUseful for: - <b>Serve</b> LLM, voice, image or video <b>models</b> <b>locally</b> behind one <b>API</b>.\n- Point <b>OpenAI</b>","status":"active","categories":["T09"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6VBWA3FXDKHKK1R2Q364Y8B","api_url":"https://veyrul.com/v1/records/src_01M6VBWA3FXDKHKK1R2Q364Y8B","updated_at":"2026-11-07T16:01:17.899Z","score":2.3945}},{"kind":"record","record":{"id":"src_01M6V4XND49NYJGKXMNQPYHVRB","type":"source","title":"Open WebUI: self-hosted AI platform, README install and licence notes","summary":"The README presents Open WebUI as a self-hosted platform built to run entirely offline, connecting local models through Ollama or OpenAI-compatible APIs.","snippet":"hosted platform built to run entirely offline, connecting <b>local</b> <b>models</b> through Ollama or <b>OpenAI</b>-<b>compatible</b> <b>APIs</b>. What it supplies: The README presents Open WebUI","status":"active","categories":["T09"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6V4XND49NYJGKXMNQPYHVRB","api_url":"https://veyrul.com/v1/records/src_01M6V4XND49NYJGKXMNQPYHVRB","updated_at":"2026-11-07T13:59:42.207Z","score":1.1905}},{"kind":"record","record":{"id":"src_01M6K4HAN5XNMZ9G90CTMWEWNN","type":"source","title":"vllm-sr/vela2-studio","summary":"Hugging Face Space vllm-sr/vela2-studio at revision fe79a19de200: SDK docker; declared licence not declared; access gating not reported. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face Space <b>vllm</b>-sr/vela2-studio at revision fe79a19de200: SDK docker; declared licence not declared; access gating not reported. Metadata-only index entry; not tested guidance. created","status":"active","categories":["T09"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6K4HAN5XNMZ9G90CTMWEWNN","api_url":"https://veyrul.com/v1/records/src_01M6K4HAN5XNMZ9G90CTMWEWNN","updated_at":"2026-11-04T11:19:02.525Z","score":0.3935}},{"kind":"record","record":{"id":"src_01M6HYBYRVGZTDMCKDQGWTNTCQ","type":"source","title":"vllm-sr/Decision-Box","summary":"Hugging Face Space vllm-sr/Decision-Box at revision a8c57a0880d7: SDK static; declared licence not declared; access gating not reported. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face Space <b>vllm</b>-sr/Decision-Box at revision a8c57a0880d7: SDK static; declared licence not declared; access gating not reported. Metadata-only index entry; not tested guidance. created","status":"active","categories":["T09"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6HYBYRVGZTDMCKDQGWTNTCQ","api_url":"https://veyrul.com/v1/records/src_01M6HYBYRVGZTDMCKDQGWTNTCQ","updated_at":"2026-11-04T00:12:00.625Z","score":0.3935}},{"kind":"record","record":{"id":"src_01M6H8RKZMWB5GAXAZN4363MJF","type":"source","title":"Alpha-VLLM/Lumina-Image-2.0","summary":"Hugging Face Space Alpha-VLLM/Lumina-Image-2.0 at revision 1f67efca23cb: SDK gradio; declared licence not declared; access gating not reported. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face Space Alpha-<b>VLLM</b>/Lumina-Image-2.0 at revision 1f67efca23cb: SDK gradio; declared licence not declared; access gating not reported. Metadata-only index entry; not tested guidance. created","status":"active","categories":["T09"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6H8RKZMWB5GAXAZN4363MJF","api_url":"https://veyrul.com/v1/records/src_01M6H8RKZMWB5GAXAZN4363MJF","updated_at":"2026-11-03T17:54:26.878Z","score":0.3935}},{"kind":"record","record":{"id":"src_01M6GGQ28C23MA9SK7SQED98G2","type":"source","title":"vllm-sr/d3-ultra","summary":"Hugging Face Space vllm-sr/d3-ultra at revision e1c3936fb46a: SDK static; declared licence not declared; access gating not reported. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face Space <b>vllm</b>-sr/d3-ultra at revision e1c3936fb46a: SDK static; declared licence not declared; access gating not reported. Metadata-only index entry; not tested guidance. created","status":"active","categories":["T09"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6GGQ28C23MA9SK7SQED98G2","api_url":"https://veyrul.com/v1/records/src_01M6GGQ28C23MA9SK7SQED98G2","updated_at":"2026-11-03T10:54:10.150Z","score":0.3935}},{"kind":"record","record":{"id":"src_01M6FC1Q6B28XCVRE36ANPF8JG","type":"source","title":"Alpha-VLLM/Lumina-Next-T2I","summary":"Hugging Face Space Alpha-VLLM/Lumina-Next-T2I at revision a169d4a9750c: SDK gradio; declared licence not declared; access gating not reported. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face Space Alpha-<b>VLLM</b>/Lumina-Next-T2I at revision a169d4a9750c: SDK gradio; declared licence not declared; access gating not reported. Metadata-only index entry; not tested guidance. created","status":"active","categories":["T09"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6FC1Q6B28XCVRE36ANPF8JG","api_url":"https://veyrul.com/v1/records/src_01M6FC1Q6B28XCVRE36ANPF8JG","updated_at":"2026-11-03T00:13:21.961Z","score":0.3935}},{"kind":"record","record":{"id":"src_01M6CDGZD0RCFKXKNCJHDE5A2P","type":"source","title":"vllm-sr/decision-studio","summary":"Hugging Face Space vllm-sr/decision-studio at revision 53d0a86905f1: SDK docker; declared licence not declared; access gating not reported. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face Space <b>vllm</b>-sr/decision-studio at revision 53d0a86905f1: SDK docker; declared licence not declared; access gating not reported. Metadata-only index entry; not tested guidance. created","status":"active","categories":["T09"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6CDGZD0RCFKXKNCJHDE5A2P","api_url":"https://veyrul.com/v1/records/src_01M6CDGZD0RCFKXKNCJHDE5A2P","updated_at":"2026-11-01T20:41:27.164Z","score":0.3935}},{"kind":"record","record":{"id":"src_01M6J3X5H737MZ5P065KD0TES4","type":"source","title":"vllm-sr/vela-studio","summary":"Hugging Face Space vllm-sr/vela-studio at revision 7e09941eca05: SDK docker; declared licence not declared; access gating not reported. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face Space <b>vllm</b>-sr/vela-studio at revision 7e09941eca05: SDK docker; declared licence not declared; access gating not reported. Metadata-only index entry; not tested guidance. created","status":"active","categories":["T09"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6J3X5H737MZ5P065KD0TES4","api_url":"https://veyrul.com/v1/records/src_01M6J3X5H737MZ5P065KD0TES4","updated_at":"2026-11-04T01:48:47.483Z","score":0.3935}},{"kind":"record","record":{"id":"src_01M64N26C6KYBV1090DVB3QY0E","type":"source","title":"Alpha-VLLM/Lumina-mGPT-2.0","summary":"Hugging Face model Alpha-VLLM/Lumina-mGPT-2.0 at revision 3d541ea5eceb: text-to-image; declared licence apache-2.0; not gated. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face <b>model</b> Alpha-<b>VLLM</b>/Lumina-mGPT-2.0 at revision 3d541ea5eceb: text-to-image; declared licence apache-2.0; not gated. Metadata-only index entry; not tested guidance. created","status":"active","categories":["T05"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M64N26C6KYBV1090DVB3QY0E","api_url":"https://veyrul.com/v1/records/src_01M64N26C6KYBV1090DVB3QY0E","updated_at":"2026-10-29T20:19:15.935Z","score":0.3934}},{"kind":"record","record":{"id":"src_01M63027SHS03Q90P1B5WNV4CY","type":"source","title":"Alpha-VLLM/Lumina-Video-f24R960","summary":"Hugging Face model Alpha-VLLM/Lumina-Video-f24R960 at revision 233fed1320ad: text-to-video; declared licence apache-2.0; not gated. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face <b>model</b> Alpha-<b>VLLM</b>/Lumina-Video-f24R960 at revision 233fed1320ad: text-to-video; declared licence apache-2.0; not gated. Metadata-only index entry; not tested guidance. created","status":"active","categories":["T06"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M63027SHS03Q90P1B5WNV4CY","api_url":"https://veyrul.com/v1/records/src_01M63027SHS03Q90P1B5WNV4CY","updated_at":"2026-10-29T04:53:02.831Z","score":0.3934}},{"kind":"record","record":{"id":"src_01M65RXH8QKZER907WESRZTWGJ","type":"source","title":"Alpha-VLLM/Lumina-T2Music","summary":"Hugging Face model Alpha-VLLM/Lumina-T2Music at revision 79615fdfa80c: text-to-audio; library transformers; declared licence apache-2.0; not gated. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face <b>model</b> Alpha-<b>VLLM</b>/Lumina-T2Music at revision 79615fdfa80c: text-to-audio; library transformers; declared licence apache-2.0; not gated. Metadata-only index entry; not tested guidance. created","status":"active","categories":["T09"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M65RXH8QKZER907WESRZTWGJ","api_url":"https://veyrul.com/v1/records/src_01M65RXH8QKZER907WESRZTWGJ","updated_at":"2026-10-30T06:45:51.932Z","score":0.3934}},{"kind":"record","record":{"id":"src_01M63FDX3CB2K26YK0209C1TT4","type":"source","title":"Alpha-VLLM/Lumina-Next-SFT-diffusers","summary":"Hugging Face model Alpha-VLLM/Lumina-Next-SFT-diffusers at revision 0ee5ec90043a: text-to-image; library diffusers; declared licence apache-2.0; not gated. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face <b>model</b> Alpha-<b>VLLM</b>/Lumina-Next-SFT-diffusers at revision 0ee5ec90043a: text-to-image; library diffusers; declared licence apache-2.0; not gated. Metadata-only index entry; not tested guidance. created","status":"active","categories":["T05"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M63FDX3CB2K26YK0209C1TT4","api_url":"https://veyrul.com/v1/records/src_01M63FDX3CB2K26YK0209C1TT4","updated_at":"2026-10-29T09:21:33.757Z","score":0.3934}},{"kind":"record","record":{"id":"src_01M64M088DB6G3Z4E8WM1CVY9A","type":"source","title":"vllm-sr/mmbert32k-factcheck-classifier-merged","summary":"Hugging Face model vllm-sr/mmbert32k-factcheck-classifier-merged at revision 88b7e3c300d1: text-classification; library transformers; declared licence apache-2.0; base vllm-sr/mmbert-32k-yarn; not gated; quantized variant. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face <b>model</b> <b>vllm</b>-sr/mmbert32k-factcheck-classifier-merged at revision 88b7e3c300d1: text-classification; library transformers; declared licence apache-2.0; base <b>vllm</b>-sr/mmbert-32k-yarn; not gated; quantized variant. Metadata-only","status":"active","categories":["T09"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M64M088DB6G3Z4E8WM1CVY9A","api_url":"https://veyrul.com/v1/records/src_01M64M088DB6G3Z4E8WM1CVY9A","updated_at":"2026-10-29T20:00:43.752Z","score":0.3934}},{"kind":"record","record":{"id":"src_01M64WA5SNXYK0NWVQBA9DEK1H","type":"source","title":"vllm-sr/Vela-1.0-Encoder-307M-Embedding","summary":"Hugging Face model vllm-sr/Vela-1.0-Encoder-307M-Embedding at revision 290318fdefda: sentence-similarity; library sentence-transformers; declared licence apache-2.0; base vllm-sr/Vela-1.0-Encoder-307M; not gated; finetune variant. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face <b>model</b> <b>vllm</b>-sr/Vela-1.0-Encoder-307M-Embedding at revision 290318fdefda: sentence-similarity; library sentence-transformers; declared licence apache-2.0; base <b>vllm</b>-sr/Vela-1.0-Encoder-307M; not gated; finetune variant. Metadata","status":"active","categories":["T09"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M64WA5SNXYK0NWVQBA9DEK1H","api_url":"https://veyrul.com/v1/records/src_01M64WA5SNXYK0NWVQBA9DEK1H","updated_at":"2026-10-29T22:25:57.505Z","score":0.3933}},{"kind":"record","record":{"id":"src_01M6617HRGABDDK9FFMZJK86VE","type":"source","title":"vllm-sr/d3","summary":"Hugging Face model vllm-sr/d3 at revision 20f37b9a892a: zero-shot-classification; library transformers; declared licence apache-2.0; base Qwen/Qwen3.8-27B; not gated; finetune variant. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face <b>model</b> <b>vllm</b>-sr/d3 at revision 20f37b9a892a: zero-shot-classification; library transformers; declared licence apache-2.0; base Qwen/Qwen3.8-27B; not gated; finetune variant. Metadata-only index entry","status":"active","categories":["T09"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6617HRGABDDK9FFMZJK86VE","api_url":"https://veyrul.com/v1/records/src_01M6617HRGABDDK9FFMZJK86VE","updated_at":"2026-10-30T09:11:08.771Z","score":0.3933}},{"kind":"record","record":{"id":"src_01M64KZHMX2PBD1JZXFG3GF6EQ","type":"source","title":"vllm-sr/d3-mini","summary":"Hugging Face model vllm-sr/d3-mini at revision bd0090dd758d: zero-shot-classification; library transformers; declared licence apache-2.0; base Qwen/Qwen3.5-4B; not gated; finetune variant. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face <b>model</b> <b>vllm</b>-sr/d3-mini at revision bd0090dd758d: zero-shot-classification; library transformers; declared licence apache-2.0; base Qwen/Qwen3.5-4B; not gated; finetune variant. Metadata-only index entry","status":"active","categories":["T09"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M64KZHMX2PBD1JZXFG3GF6EQ","api_url":"https://veyrul.com/v1/records/src_01M64KZHMX2PBD1JZXFG3GF6EQ","updated_at":"2026-10-29T20:00:20.597Z","score":0.3933}},{"kind":"record","record":{"id":"src_01M6CJDTWG7Q2F5JREXHBMPKVQ","type":"source","title":"Alpha-VLLM/Lumina-mGPT-2.0-Omni","summary":"Hugging Face model Alpha-VLLM/Lumina-mGPT-2.0-Omni at revision ce2b9937f0b2: image-to-image; declared licence apache-2.0; not gated. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face <b>model</b> Alpha-<b>VLLM</b>/Lumina-mGPT-2.0-Omni at revision ce2b9937f0b2: image-to-image; declared licence apache-2.0; not gated. Metadata-only index entry; not tested guidance. declared lineage (declared","status":"active","categories":["T05"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6CJDTWG7Q2F5JREXHBMPKVQ","api_url":"https://veyrul.com/v1/records/src_01M6CJDTWG7Q2F5JREXHBMPKVQ","updated_at":"2026-11-01T22:07:07.114Z","score":0.3933}},{"kind":"record","record":{"id":"src_01M6714Y8BPQTPM8PR6GAK709T","type":"source","title":"vllm-sr/mmbert-embed-32k-2d-matryoshka","summary":"Hugging Face model vllm-sr/mmbert-embed-32k-2d-matryoshka at revision 6a1c7732cd05: sentence-similarity; library sentence-transformers; declared licence apache-2.0; base vllm-sr/mmbert-32k-yarn; not gated; quantized variant. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face <b>model</b> <b>vllm</b>-sr/mmbert-embed-32k-2d-matryoshka at revision 6a1c7732cd05: sentence-similarity; library sentence-transformers; declared licence apache-2.0; base <b>vllm</b>-sr/mmbert-32k-yarn; not gated; quantized variant. Metadata","status":"active","categories":["T09"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6714Y8BPQTPM8PR6GAK709T","api_url":"https://veyrul.com/v1/records/src_01M6714Y8BPQTPM8PR6GAK709T","updated_at":"2026-10-30T18:28:57.700Z","score":0.3933}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M6VVM14PS4BVTG89KP9KHPEK","type":"article","revision":1,"title":"Serve a local model with vLLM through an OpenAI-compatible API","coverage":"For writers and pipeline builders who already use the OpenAI chat format and want a small model on their own Linux machine. You end with a running server and a short Python client. It follows the vLLM quickstart and was not run.","example":"A hypothetical client asks a small served model for three lighthouse ghost story titles; nothing was run and the model output was not observed.","tips":["The server applies the model repository's generation_config.json by default, so sampling may differ from vLLM's own defaults.","If you start the server with an API key, send that key from the client instead of a placeholder.","A slow first start can come from kernels being compiled at startup, which a separate precompiled-kernels step avoids."],"categories":["T09","T04"],"tags":["vllm","openai-compatible","local-models","linux","api-server","chat-completions","python"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}}],"truncated":true,"has_more":true,"next_cursor":"eyJyZWZlcmVuY2UiOiJNakEiLCJwcmV2aWV3IjpudWxsLCJxIjoiU2VydmUgYSBsb2NhbCBtb2RlbCB3aXRoIHZMTE0gdGhyb3VnaCBhbiBPcGVuQUktY29tcGF0aWJsZSBBUEkiLCJ0eXBlcyI6W10sImNhdGVnb3JpZXMiOltdfQ","ordering":"bounded_reference_and_preview_lanes"}