Pinned Repositories
OpenRLHF
An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & Mixtral)
bun
Incredibly fast JavaScript runtime, bundler, test runner, and package manager – all in one
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
tensorflow
An Open Source Machine Learning Framework for Everyone
es
A JavaScript interpreter from scratch, supporting ES5 syntax.
faster-nougat
Implementation of nougat that focuses on processing pdf locally.
NP_ML
A tool library of classical machine learning algorithms with only numpy.
pdf-with-its-own-md5
A PDF template that contains its own MD5!
ring-flash-attention
Ring attention implementation with flash attention
whisper-openvino
openvino version of openai/whisper
zhuzilin's Repositories
zhuzilin/ring-flash-attention
Ring attention implementation with flash attention
zhuzilin/whisper-openvino
openvino version of openai/whisper
zhuzilin/faster-nougat
Implementation of nougat that focuses on processing pdf locally.
zhuzilin/pdf-with-its-own-md5
A PDF template that contains its own MD5!
zhuzilin/es
A JavaScript interpreter from scratch, supporting ES5 syntax.
zhuzilin/chatgpt-desktop
Desktop version of ChatGPT, support manually set cookie
zhuzilin/aqt-pytorch
zhuzilin/wandb-discord-bot
A discord bot for monitoring wandb project and runs.
zhuzilin/blog
my blog~
zhuzilin/llama
Inference code for LLaMA models
zhuzilin/torchrec_mapper
zhuzilin/zhuzilin
zhuzilin/electron-fc
A electron based famicom(NES) emulator
zhuzilin/flash-attention
Fast and memory-efficient exact attention
zhuzilin/nvcc_daxpy_example
zhuzilin/scattermoe
Triton-based implementation of Sparse Mixture of Experts.
zhuzilin/triton
Development repository for the Triton language and compiler
zhuzilin/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
zhuzilin/base64-img
zhuzilin/bun
Incredibly fast JavaScript runtime, bundler, transpiler and package manager – all in one.
zhuzilin/chibicc
A small C compiler
zhuzilin/FBGEMM
FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/
zhuzilin/gpt-neox
An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
zhuzilin/grouped_gemm
PyTorch bindings for CUTLASS grouped GEMM.
zhuzilin/instruct-eval
This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.
zhuzilin/megablocks
zhuzilin/OpenRLHF
An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & Mixtral)
zhuzilin/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
zhuzilin/qiskit-translations
Home of Qiskit documentation translations
zhuzilin/torchrec
Pytorch domain library for recommendation systems