- HongKong
- https://zhengpeirong.github.io/
Lists (11)
Sort Name ascending (A-Z)
Starred repositories
An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)
Train transformer language models with reinforcement learning.
A highly optimized LLM inference acceleration engine for Llama and its variants.
SGLang is a fast serving framework for large language models and vision language models.
A collection of awesome text-to-image generation studies.
cross platform C++ library for hardware information (CPU, RAM, GPU, ...)
[CVPR 2023] DepGraph: Towards Any Structural Pruning
A curated list of awesome edge computing, including Frameworks, Simulators, Tools, etc.
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
π€ Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
Evaluating LLMs with fewer examples
π¨ ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.
Tips for Writing a Research Paper using LaTeX
A framework for few-shot evaluation of language models.
nnScaler: Compiling DNN models for Parallel Training
Open source code in the field of semantic communication.
π A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
TPI-LLM: Serving 70b-scale LLMs Efficiently on Low-resource Edge Devices
Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. arXiv:2408.07666.
π« A curated list of Model Merging methods.
Download the latest stable Synergy binaries.
Awesome LLMs on Device: A Comprehensive Survey
A curated list of research in System for Edge Intelligence and Computing(Edge MLSys), including Frameworks, Tools, Repository, etc. Paper notes are also provided.
INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model
Deep Learning papers reading roadmap for anyone who are eager to learn this amazing tech!