Inferact
@inferact
Building the future of inference through @vllm_project
参加 December 2025
5 フォロー中 7K ファン
Day-0 support for DeepSeek v4.1 Flash landed across H100, H200, B200, B300, GB200, and GB300. Thank you to @SemiAnalysis_ for verifying this independently and @NVIDIAAI for the collab.
Serving recipes here:
もっと見る
On the Day 0 release of DeepSeekv4.1 Flash, NVIDIA vLLM works out of the box with zero issues across all 6 SKUs: H100, H200, B200, B300, GB200, GB300! Amazing work by the NVIDIA & Inferact teams! In comparison, AMD vLLM still does not work on DeepSeekv4.1 Flash, as we will describe below👇️(1/2)🧵
もっと見る
