huyphan168

PEER

Mixture of A Million Experts

LegalChat

Building a chatbot for legal banking documents using Langchain and OpenAI API

EasyCuda

EasyCuda: A Comprehensive Guide to Accelerated and Parallel Programming with CUDA and C/C++

Implicit-Modeling

Implementation of paper State-driven Implicit Modeling

Sobel-Verilog

Implementation of Sobel Operation using AXIS protocol and buffer with 1 MAC.

FlexGen-X

Extend FlexGen for supporting Flan-T5, GPT-J, GPT-NeoX, LLaMa, BLIP-v2, CodeGen, BLOOM. Enhance Inference with OpenAI Triton Custom Kernel.

Robust-S4-Pose

We introduce Structured-State-Space Model with Bayesian filtering in state space for robust 3D human pose estimation.

FiD-Zalo

Fusion-in Decoder for Vietnamese

ViQA-toolkit

Open-domain question answering toolkit for Vietnamese

deepchem

Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology

Equidock_enhance

Efficient and Faster data preparation with multi-gpu training version of Equidock

FasterComputing

huyphan168.github.io

Github Pages for Nhat Huy Phan

Implicit-SlotAttention

Unofficial Implementation of Object Representation as Fixed Points

InvertedPenCart-Simulink

Control Inverted Pendulum using Linearized Plant and Cascade Control System

LlamaAcademy

A school for camelids

LLM-Tuner

Data collection pipeline and Fully Efficient Sharded Distributed Training for Text Generation Lehrer's models

MultiNav

Efficient Multi-languages Code Navigation Python Package

robustqa

Robust Question Answering with LoRA Fine-Tuning and Text Augmentation

Verilog-DL

Verilog or VHDL implementation of Deep Learning algorithms on Xilinx FPGA boards + Vivado synthesis.

3DTumorReconstruct

chatbot-ui

The open-source AI chat app for everyone.

experiments

Open sourced predictions, execution logs, trajectories, and results from model inference + evaluation runs on the SWE-bench task.

FasterTransformer-CUDA

Transformer related optimization, including BERT, GPT, MPT

RAS-LLM

Description of Retrieve, Abstraction and Search approach for reasoning with abstraction

RepoPilot

Repo-Level Coding Assistant that Can Understand Your Whole Codebase

ring-flash-attention

Ring attention implementation with flash attention

vision-js

vllm-x

Adding new features to vllm

vllm-z