shkim-emily

mamba.c

Inference of Mamba models in pure C

containers

riscv-vectorized-benchmark-suite

RISC-V Vectorized Bencmark Suite. based on https://github.com/RALC88/riscv-vectorized-benchmark-suite

intel-extension-for-transformers

⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡

ara

The PULP Ara is a 64-bit Vector Unit, compatible with the RISC-V Vector Extension Version 1.0, working as a coprocessor to CORE-V's CVA6 core

llama.cpp

LLM inference in C/C++

riscv-llm

Pytorch_mixture-of-experts

PyTorch implementation of moe, which stands for mixture of experts

transfomers-silicon-research

Research and Materials on Hardware implementation of Transformer Model

fastllm

A collection of LLM services you can self host via docker or modal labs to support your applications development

instructor

structured outputs for llms

minstructor

get structured objects from LLMs -- teaching implementation of the instructor library in python

tinyhnsw

build your own vector database -- the littlest hnsw

ece284fa22