ChangyiYang/changyiyang.github.io
Decks & proposals — full-duplex 语音交互方向的提案与调研
Decks & proposals — full-duplex 语音交互方向的提案与调研
Audition page for assistant-interrupt examples in zetianli/FD_data_v2
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
SGLang is a fast serving framework for large language models and vision language models.
Allow torch tensor memory to be released and resumed later
A unified framework for building, running, and training general agents at scale.
Dataflow-Oriented Reinforcement Learning for (Multi-)Agentic LLMs
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Official implementation of the paper "Length Value Model: Pretraining Value Model for Scalable Length Prediction and Control"
Learning TileLang with 10 puzzles!
Distributed RL System for LLM Reasoning
A simple profile
slime is an LLM post-training framework for RL Scaling.
Accelerating MoE with IO and Tile-aware Optimizations
My learning notes/codes for ML SYS.
[ICLR'25] Official code for the paper 'MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs'
17-214/514 s2024 lab02
For CS189 Project