yinqiwen

the-algorithm

Source code for Twitter's Recommendation Algorithm

llama2.c

Inference Llama 2 in one file of pure C

candle

Minimalist ML framework for Rust

the-algorithm-ml

Source code for Twitter's Recommendation Algorithm

burn

Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.

vespa

AI + Data, online. https://vespa.ai

gifski

GIF encoder based on libimagequant (pngquant). Squeezes maximum possible quality from the awful GIF format.

highway

Performance-portable, length-agnostic SIMD with runtime dispatch

tower

async fn(Request) -> Result<Response, Error>

tarpc

An RPC framework for Rust with a focus on ease of use.

stable-diffusion.cpp

Stable Diffusion in pure C/C++

rkyv

Zero-copy deserialization framework for Rust

zep

Zep: Long-Term Memory for ‍AI Assistants.

souper

A superoptimizer for LLVM IR

lightllm

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

S-LoRA

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

MatX

An efficient C++17 GPU numerical computing library with Python-like syntax

simdutf

Unicode routines (UTF8, UTF16, UTF32) and Base64: billions of characters per second using SSE2, AVX2, NEON, AVX-512, RISC-V Vector Extension. Part of Node.js and Bun.

SimSIMD

Up to 200x Faster Inner Products and Vector Similarity — for Python, JavaScript, Rust, C, and Swift, supporting f64, f32, f16 real & complex, i8, and binary vectors using SIMD for both x86 AVX2 & AVX-512 and Arm NEON & SVE 📐

splinterdb

High Performance Embedded Key-Value Store

mlir-tutorial

MLIR For Beginners tutorial

lingoose

🪿 LinGoose is a Go framework for building awesome AI/LLM applications.

xor_singleheader

Header-only binary fuse and xor filter library

lzav

Fast In-Memory Data Compression Algorithm (inline C/C++) 460+MB/s compress, 2500+MB/s decompress, ratio% better than LZ4, Snappy, and Zstd@-1

hermetic_cc_toolchain

Bazel C/C++ toolchain for cross-compiling C/C++ programs

libgavran

Experimenting with persistence in C

hdt-cpp

HDT C++ Library and Tools

DYNAMIC

Dynamic succinct/compressed data structures

bit_vector

Fast and highly tuned bit vector implementation including space efficient rank and select support having only 3.51% space overhead.

quad-wavelet-tree