chiennv2000

Chien Nguyen's starred repositories

mlc-llm

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

Language:PythonApache-2.016840 160 1013

flash-attention

Fast and memory-efficient exact attention

Language:PythonBSD-3-Clause10750 104 779

readme-md-generator

📄 CLI that generates beautiful README.md files

Language:JavaScriptMIT10738 74 101

NeMo

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Language:PythonApache-2.010040 183 2049

shell_gpt

A command-line productivity tool powered by AI large language models like GPT-4, will help you accomplish your tasks faster and more efficiently.

Language:PythonMIT8261 78 274

unsloth

Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory

Language:PythonApache-2.06694 54 264

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

Language:C++Apache-2.06510 81 1212

OLMo

Modeling, training, eval, and inference code for OLMo

Language:PythonApache-2.03947 40 138

AutoGPTQ

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

Language:PythonMIT3754 32 398

mergekit

Tools for merging pretrained large language models.

Language:PythonLGPL-3.03327 40 199

llmware

Providing enterprise-grade LLM-based development framework, tools, and fine-tuned models.

Language:PythonApache-2.03107 38 103

lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

Language:PythonApache-2.02253 22 724

datatrove

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

Language:PythonApache-2.01238 39 48

Olive

Olive is an easy-to-use hardware-aware model optimization tool that composes industry-leading techniques across model compression, optimization, and compilation.

Language:PythonMIT1211 26 129