Fast Neural Machine Translation in C++

MiroThinker is an open-source search agent model, built for tool-augmented reasoning and real-world information seeking, aiming to match the deep research experience of OpenAI Deep Research and Gem…

A Rust port of FlameGraph

A heap memory profiler for Linux

Rust without the borrow checker

Z80-μLM is a 2-bit quantized language model small enough to run on an 8-bit Z80 processor. Train conversational models in Python, export them as CP/M .COM binaries, and chat with your vintage compu…

A high-performance, concurrent hash table

Fast integer compression in C using the StreamVByte codec

Advanced Matrix Extensions (AMX) Guide

GIT utilities -- repo summary, repl, changelog population, author commit percentages and more

Access Arm64 CPU system registers

TouchGAL是立足于分享快乐的一站式Galgame文化社区, 为Gal爱好者提供一片净土!

This repository is a read-only mirror of https://gitlab.arm.com/kleidi/kleidiai

A stand-alone implementation of several NumPy dtype extensions used in machine learning.

Low-bit LLM inference on CPU/NPU with lookup table

Fast Matrix Multiplications for Lookup Table-Quantized LLMs

A fast JSON serializing & deserializing library, accelerated by SIMD.

FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/

Exploring the scalable matrix extension of the Apple M4 processor

Free and Open Source, Distributed, RESTful Search Engine

Cross-platform, customizable multimedia/video processing framework. With strong GPU acceleration, heterogeneous design, multi-language support, easy to use, multi-framework compatible and high perf…

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

Contexts Optical Compression

A Lightweight Recommendation System

Arm C Language Extensions (ACLE)

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance…

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

SGLang is a high-performance serving framework for large language models and multimodal models.