flashinfer alternatives
Tools that could take the place of flashinfer, ranked by the stacks builders put them in rather than by stars alone.
Other runtimes in the runchr registry that do the work of flashinfer — a tool somebody pairs with it ranks above a more popular stranger. Read the flashinfer page or browse every runtimes.
A high-throughput inference and serving engine for GPUs.
Optimized inference runtime for LLMs and visual gen models on NVIDIA GPUs.
CLI proxy that compresses shell command output before it reaches an LLM.
Local AI server serving optimized LLMs on GPUs and NPUs via OpenAI-compatible
OpenAI/Anthropic-compatible MLX inference server for Apple Silicon tuned
Local MLX inference server that serves open models to Claude Code via Anthropic
Fast local LLM inference engine for Apple Silicon with native MTP speculative
Run huge MoE models privately on your own GPUs with OpenAI-compatible API.
Native local LLM inference server for Apple Silicon with OpenAI and Anthropic
Local Qwen3.8-Flash-Next inference server for AMD Strix Halo with OpenAI
Run open models locally and serve an OpenAI-compatible API.
Run quantised models locally, with an OpenAI-compatible server.