kkangle

raft

RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.

distributed-llama

Tensor parallelism is all you need. Run LLMs on weak devices or make powerful devices even more powerful by distributing the workload and dividing the RAM usage.

stable-dreamfusion

Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

Megatron-LM

Ongoing research training transformer models at scale

candle

Minimalist ML framework for Rust

zkml

zkevm-circuits

ministark

🏃‍♂️💨 GPU accelerated STARK prover built on @arkworks-rs

winterfell

A STARK prover and verifier for arbitrary computations

Transformer

Transformer seq2seq model, program that can build a language translator from parallel corpus

freedom

Source files for SiFive's Freedom platforms

riscv-openwrt

Porting OpenWrt to RISC-V - please check https://github.com/xfguo/riscv-openwrt-port for full instructions.

rocket-chip

Rocket Chip Generator

pyimagej

Use ImageJ from Python

imglib2-imglyb

MBSP

Memory-based shallow parser for Python

sos

SoS workflow system for daily data analysis

scijava-jupyter-kernel

[RETIRED] Try IJava or BeakerX