An Optimizer for Nvidia Compilers.

Custom inference engine to run Minimax-M2.X series of models on dual RTX Pro 6000 (sm120)

QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning

A vLLM patch + hand‑written SM120 SASS kernels: 2‑bit MoE experts + an FP4 "delta" cache that recovers precision — matching the official (NV)FP4 checkpoint's quality on consumer Blackwell cards

A Collection of Personal Scripts

A small C compiler

A fast, simple & powerful blog framework, powered by Node.js.

TokenSpeed is a speed-of-light LLM inference engine.

Compile docker images into a single self-contained binary

An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs

Custom 6.61 PSP Firmware for the PSVita PSP Emulator

LLM RP TUI for Power Users.

A framework for modding and instrumenting games.

🔩 Rust bindings to Elden Ring, Dark Souls 3, Nightreign and Sekiro

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

Stockfish NNUE (Chess evaluation) trainer in Pytorch

A free and strong UCI chess engine

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

µlight or "u-light" is a zero-dependency, lightweight, and portable syntax highlighter.

🐱 A simple cat-like/library syntax highlighter made in C

LLM model quantization (compression) toolkit with HW acceleration support for Nvidia, AMD, Intel GPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.

English light novel release dates

An official continuation of https://github.com/djoslin0/sm64ex-coop on sm64coopdx for the enhancements and progress it already has.

A fast usermode x86 and x86-64 emulator for Arm64 Linux

Monero: the secure, private, untraceable cryptocurrency

Quantization, kernels, runtime and inference engine for mobiles, wearables, smart home and robots.