SGLang is a fast serving framework for large language models and vision language models.

A curated list of reinforcement learning with human feedback resources (continually updated)

A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 and reasoning techniques.

Adding support for `logit_bias` to vLLM, A high-throughput and memory-efficient inference and serving engine for LLMs

The official Genbench Collaborative Benchmarking Task repository 2024

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

A framework for few-shot evaluation of autoregressive language models, with support for OPT-30b

Production build of the new website

Scribed notes for the [IFT6085] Deep Learning Theory course at UdeM

A Jekyll version of the Clean Blog theme by Start Bootstrap

Useful extra functionality for TensorFlow 2.0 maintained by SIG-addons

Label Studio is a multi-type data labeling and annotation tool with standardized output format

Translation of VIP cheatsheets https://stanford.edu/~shervine/teaching/cs-229.html