{"type":"post","id":"nvidia-adds-official-sglang-instructions-for-the-nvfp4-00fbd0","slug":"nvidia-adds-official-sglang-instructions-for-the-nvfp4-00fbd0","title":"NVIDIA adds official SGLang instructions for the NVFP4 DeepSeek checkpoint","description":"NVIDIA’s model-card update documents native SGLang support for its NVFP4 DeepSeek-V4.1-Flash-1017 checkpoint, alongside the previously documented vLLM path.","retrieval_nugget":"NVIDIA’s model-card update documents native SGLang support for its NVFP4 DeepSeek-V4.1-Flash-1017 checkpoint, alongside the previously documented vLLM path. The launch example was validated on four GB300 GPUs and includes a host-memory setting for Engram tables, giving Blackwell operators a second documented route to serve this checkpoint.","published_at":"2026-11-14","updated_at":"2026-11-14","record_date":"2026-11-14","date_kind":"published_at","topics":["inference","open-models"],"entities":["NVIDIA","SGLang","vLLM","DeepSeek-V4.1-Flash-1017-NVFP4","DeepSeek"],"related_patterns":[],"novelty_label":"new_fact","what_changed":"NVIDIA added official SGLang deployment instructions for its previously published NVFP4 DeepSeek checkpoint.","prior_refs":["https://newruntime.com/posts/nvidia-has-published-an-nvfp4-quantized-deepseek-v4-a06093/"],"source_url":"https://huggingface.co/nvidia/DeepSeek-V4.1-Flash-1017-NVFP4/commit/3ae9c0d3fbbea5370bd06e679d22044db15883f1","source_urls":["https://huggingface.co/nvidia/DeepSeek-V4.1-Flash-1017-NVFP4/commit/3ae9c0d3fbbea5370bd06e679d22044db15883f1"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:nvidia-adds-official-sglang-instructions-for-the-nvfp4-00fbd0","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/nvidia-adds-official-sglang-instructions-for-the-nvfp4-00fbd0/","markdown":"https://newruntime.com/posts/nvidia-adds-official-sglang-instructions-for-the-nvfp4-00fbd0.md","json":"https://newruntime.com/posts/nvidia-adds-official-sglang-instructions-for-the-nvfp4-00fbd0.json"},"markdown_url":"https://newruntime.com/posts/nvidia-adds-official-sglang-instructions-for-the-nvfp4-00fbd0.md","next_reads":[{"type":"topic","path":"/topics/inference/","url":"https://newruntime.com/topics/inference/","title":"Inference","reason":"Explore the inference topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/inference.md","json_url":"https://newruntime.com/topics/inference.json"},{"type":"topic","path":"/topics/open-models/","url":"https://newruntime.com/topics/open-models/","title":"Open Models","reason":"Explore the open-models topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/open-models.md","json_url":"https://newruntime.com/topics/open-models.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}