Feng Yao

Implementation for FP8/INT8 Rollout for RL training without performence drop.

Official implementation for DenseMixer: Improving MoE Post-Training with Precise Router Gradient

Implementation and datasets for "Training Language Models to Generate Quality Code with Program Analysis Feedback"

verl: Volcano Engine Reinforcement Learning for LLMs

Source code and dataset for AAAI2023 paper "Unsupervised Legal Evidence Retrieval via Contrastive Learning with Approximated Positive"

No description.

A repo for open research on building large reasoning models

Website for CSE 234, Winter 2025

No description.

Tools for merging pretrained large language models.

A framework for few-shot evaluation of language models.

Unify Efficient Fine-tuning of 100+ LLMs

PyTorch bindings for CUTLASS grouped GEMM.

No description.

An experimental open-source attempt to make GPT-4 fully autonomous.

No description.

A framework for training, evaluating and testing models in pytorch.