zhuohan123
🎓 CS PhD at UC Berkeley | 👨💻 Machine Learning System | Building @vllm-project
UC BerkeleyBerkeley, CA
Pinned Repositories
alpa
Training and serving large-scale neural networks with auto parallelization.
FlexGen
Running large language models on a single GPU for throughput-oriented scenarios.
FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
autodiff
A super tiny CPU single-threaded automated differentiation based on numpy.
g2-lstm
Codes for "Towards Binary-Valued Gates for Robust LSTM Training".
hint-nart
macaron-net
Codes for "Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View"
openmp-for-python
An OpenMP implementation for Python2
terapipe
zhuohan123's Repositories
zhuohan123/macaron-net
Codes for "Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View"
zhuohan123/g2-lstm
Codes for "Towards Binary-Valued Gates for Robust LSTM Training".
zhuohan123/terapipe
zhuohan123/hint-nart
zhuohan123/openmp-for-python
An OpenMP implementation for Python2
zhuohan123/autodiff
A super tiny CPU single-threaded automated differentiation based on numpy.
zhuohan123/fairseq-ray
Fairseq armed with Ray
zhuohan123/hoplite-rllib
zhuohan123/ucx-examples
Examples of OpenUCX API
zhuohan123/DL4NMT_Theano
Some Theano NMT code based on DL4NMT.
zhuohan123/DPR
Dense Passage Retriever - is a set of tools and models for open domain Q&A task.
zhuohan123/FlexGen
Running large language models like OPT-175B/GPT-3 on a single GPU. Focusing on high-throughput large-batch generation.
zhuohan123/gloo
Collective communications library with various primitives for multi-machine training.
zhuohan123/hello-world
My first Github repository
zhuohan123/homepage
My homepage content.
zhuohan123/homework_fall2020
Assignments for Berkeley CS 285: Deep Reinforcement Learning (Fall 2020)
zhuohan123/ray
A fast and simple framework for building and running distributed applications.
zhuohan123/tensorflow
An Open Source Machine Learning Framework for Everyone
zhuohan123/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
zhuohan123/zhuohan123.github.io