Materials for learning SGLang

slime is a LLM post-training framework aiming for RL Scaling.

造福广大需要动物实验的朋友

verl: Volcano Engine Reinforcement Learning for LLMs

Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team, Alibaba Cloud.

Allow torch tensor memory to be released and resumed later

Distributed RL System for LLM Reasoning

MiMo: Unlocking the Reasoning Potential of Language Model – From Pretraining to Posttraining

Udpated COPS Code Repo

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)

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

A framework for few-shot evaluation of autoregressive language models.

A series of math-specific large language models of our Qwen2 series.

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

AgentTuning: Enabling Generalized Agent Abilities for LLMs

A high-throughput and memory-efficient inference and serving engine for LLMs

SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning. COLM 2024 Accepted Paper

Build, evaluate, understand, and fix LLM-based apps