ericcurtin/vllm-vulkan

Custom LM Studio backends — run on legacy CPUs and Vulkan GPUs. AVX1, experimental no-AVX, and more. We were told it wouldn't work… so we made it work.

The vLLM XPU kernels for Intel GPU

Run LLMs on AMD Vega8 / Vega10 APUs and GPUs (Ryzen 5700G / gfx90c and Vega 56/64): ROCm 7 gfx900 backport + Vulkan/RADV launchers, Docker images, benchmarks for llama.cpp and LM Studio

A vLLM plugin built on the FlagOS unified multi-chip backend.

This will be the official ROCmFPX stack and studio

Home for the Development of MLX Vulkan backend

Community maintained hardware plugin for vLLM on Apple Silicon

LLM inference in C/C++

V100 / SM70-focused vLLM engineering fork for modern LLM inference.