An autonomous agent for deep financial research

LLM inference in C/C++

mHC kernels implemented in CUDA

Physics of Language Models: Part 4.2, Canon Layers at Scale where Synthetic Pretraining Resonates in Reality

Sampling profiler for Python programs

verl: Volcano Engine Reinforcement Learning for LLMs

My learning notes for ML SYS.

Scaling RL on advanced reasoning models

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…

DeepEP: an efficient expert-parallel communication library

FlashMLA: Efficient Multi-head Latent Attention Kernels

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)

Update ASR paper everyday

[ICLR'25 Oral] UGround: Universal GUI Visual Grounding for GUI Agents

PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.

A Zsh theme

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

A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.

Fast lexical search implementing BM25 in Python

PyMuPDF4LLM

A machine learning software for extracting information from scholarly documents

LLM101n: Let's build a Storyteller

Python SDK for the Reka AI API