kimbochen/mt-infer-bench
Multi-turn inference benchmarking
Multi-turn inference benchmarking
Lightweight harness for replaying inference traffic against an endpoint
slime is an LLM post-training framework for RL Scaling.
The Unified Machine Learning Framework
Async RL Training at Scale
An H-1B visa status checker
collection of benchmarks to measure basic GPU capabilities
A high-throughput and memory-efficient inference and serving engine for LLMs
A simple LLaMA implementation using MLX.
A PyTorch implementation of the original DDPM, with a focus on improving training efficiency.
A DIY deep learning library using the MiniTorch template.
A blog where I write about research papers and blog posts I read.
An implementation of JAX core based on Autodidax.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
An automated question answering application based on RAG.
An automatic TA that answers student questions.
Experiment of using Tangent to autodiff triton
Summarizing Emotion Triggers with TRansformers.
This repo contains the dataset for the EMNLP 2022 paper "Why Do You Feel This Way? Summarizing Triggers of Emotions in Social Media Posts"
Homework and projects of my computer vision course.
Assignment 1 of UCR CS 213 Fall 2022.
A CUDA implementation of the k-means clustering algorithm