Rocm

Open Machine Learning Compiler Framework

LMCache: Supercharge Your LLM with the Fastest KV Cache Layer

A retargetable MLIR-based machine learning compiler and runtime toolkit.

Large-scale LLM inference engine

Large-scale LLM inference engine

RDNA-native LLM inference engine in Rust.

RDNA-native LLM inference engine in Rust.

Dashboard for InferenceX™, Open Source Continuous Inference

A project repository for work on improving local LLMs on my personal AMD devices