comaniac

latex-proj-tool

A toolset to traverse and manipulate a Latex project with multiple .tex files.

epoi

Benchmark PyTorch Custom Operators

dlc-literature

hf-hub-stats

Statistics of Hugging Face hub models

llmperf

LLMPerf is a library for validating and benchmarking LLMs

vllm

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

opentuner

An extensible framework for program autotuning

tvm

Open deep learning compiler stack for cpu, gpu and specialized accelerators

accelerate

🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision

alpa

Auto parallelization for large-scale neural networks

apex

AutoFP8

comaniac.github.io

Personal Website

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

github-action-samples

mlc-llm

Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

msccl

Microsoft Collective Communication Library

NeMo

NeMo: a toolkit for conversational AI

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

raf

ratex

slapo

smoothquant

[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

tensorflow-alpa

tlcpack

torchdynamo

transformers

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

transformers-benchmarks

xformers

Hackable and optimized Transformers building blocks, supporting a composable construction.

xla

Enabling PyTorch on Google TPU