A simple C++11 Thread Pool implementation

Reference implementations of MLPerf™ inference benchmarks

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

State-of-the-art deep learning based audio codec supporting both mono 24 kHz audio and stereo 48 kHz audio.

FSA/FST algorithms, differentiable, with PyTorch compatibility.

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

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

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

A high-throughput and memory-efficient inference and serving engine for LLMs

Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)

ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型

The Mojo Programming Language

Quantized Neural Network PACKage - mobile-optimized implementation of quantized neural network operators

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

oneAPI Deep Neural Network Library (oneDNN)

Seamless operability between C++11 and Python

This is a code repository for pytorch c++ (or libtorch) tutorial.

Keyword spotting on Arm Cortex-M Microcontrollers

Official implementation of the Keyword Transformer: https://arxiv.org/abs/2104.00769

Transformer related optimization, including BERT, GPT

Visualizer for Valgrind Massif data files

webrtc audio processing

Rocket Chip Generator

Nuclei Microcontroller Software Interface Standard Development Repo

Robust Speech Recognition via Large-Scale Weak Supervision

Flops counter for convolutional networks in pytorch framework

FFT generator using Chisel