cli99

academic-kickstart

Cheng's Website

accelerate

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

acm-ccs

ACM Computing Classification System

bleve-search-react

cermine-docker

composer

Supercharge Your Model Training

flops-profiler

pytorch-profiler

hugo-cli99

llm-analysis

Latency and Memory Analysis of Transformer Models for Training and Inference

cli99/llm-analysis

Latency and Memory Analysis of Transformer Models for Training and Inference

cli99/composer

Supercharge Your Model Training

cli99/attorch

A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.

cli99/AutoFP8

cli99/AutoGPTQ

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

cli99/cutlass

CUDA Templates for Linear Algebra Subroutines

cli99/DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.

cli99/Diffusion-Models-pytorch

Pytorch implementation of Diffusion Models (https://arxiv.org/pdf/2006.11239.pdf)

cli99/KVQuant

KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

cli99/llm-awq

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

cli99/llm-compressor

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

cli99/llm-foundry

LLM training code for MosaicML foundation models

cli99/llm-scripts

cli99/marlin

FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.

cli99/megablocks

cli99/minRF

Minimal implementation of scalable rectified flow transformers, based on SD3's approach

cli99/nccl-tests

NCCL Tests

cli99/quant-matmul

cli99/sampleproject

A sample project that exists for PyPUG's "Tutorial on Packaging and Distributing Projects"

cli99/starter-academic

cli99/stk

cli99/superbenchmark

A validation and profiling tool for AI infrastructure

cli99/TensorRT-LLM

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.

cli99/theme-academic-cv

🎓 无需编写任何代码即可轻松创建漂亮的学术网站 Easily create a beautiful academic résumé or educational website using Hugo and GitHub. No code.

cli99/torchtitan

A native PyTorch Library for large model training

cli99/transformer_framework

framework for plug and play of various transformers (vision and nlp) with FSDP

cli99/TransformerEngine

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.

cli99/transformers

🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.

cli99/VILA

VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)

cli99/vllm

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