Beast code in Giters

CHU Tianxiang's repositories

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

Language:PythonApache-2.0126 40

QuIP quantization

Language:PythonGPL-3.035 2 8

llama.cpp to PyTorch Converter

Language:CudaNOASSERTION14 1 1

EXL2 quantization generalized to other models.

Language:Python600

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

Language:PythonBSD-3-Clause200

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

Language:PythonMIT100

A fast inference library for running LLMs locally on modern consumer-class GPUs

Language:PythonMIT100

Codebase for Atom

Language:Cuda000

Multi-Task Deep Neural Networks for Natural Language Understanding

Language:Python000

a tutorials for deep learning course.

Language:Jupyter Notebook000