hudengjun's repositories
WorkAccelerate
工作加速方法
easyprofiler
for a core lib from easy_profiler
ChatGLM-Tuning
一种平价的chatgpt实现方案, 基于ChatGLM-6B + LoRA
cmake-init
The missing CMake project initializer
Colab_notebooks
google colab notebooks to learn
DeepSpeedExamples
Example models using DeepSpeed
EnergonAI
Large-scale model inference.
FasterTransformer
Transformer related optimization, including BERT, GPT
kubernetes-cloud
Getting Started with the CoreWeave Kubernetes GPU Cloud
Learn-Vim
Learning Vim and Vimscript doesn't have to be hard. This is the guide that you're looking for.
lightllm
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
llama-deepspeed
train llama-30B on a single A100 80G node using 🤗 transformers and 🚀 Deepspeed Pipeline Parallelism
lmdeploy
LMDeploy is a toolkit for compressing, deploying, and serving LLM
nginx_cmake
the nginx-cmake file to quickly build cmake-vim clangd code view and debug.
nvim-lspconfig
Quickstart configurations for the Nvim LSP client
simple_vim
the most simple vim config for online docker
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.
thread-pool
A C++17 thread pool for high-performance scientific computing.
vcpkg_libs
some useful vcpkg libs not contained by current vcpkg.