verl: Flexible and Scalable Reinforcement Learning Library for LLM Reasoning and Tool-Calling
PyTorch
2,993 views
88 likes
PyTorch Expert Exchange: Efficient Generative Models: From S
PyTorch
Reinforcement Learning for Agents - Will Brown, ML Researche
AI Engineer
Will Brown: Abstractions for Agentic RL
OpenPipe
RAG vs. CAG: Solving Knowledge Gaps in AI Models
IBM Technology
LLM inference optimization: Architecture, KV cache and Flash
YanAITalk
Andrej Karpathy: Software Is Changing (Again)
Y Combinator
Build Better AI Agents with RL & Fine-Tuning (Kyle from Open
AI Tinkerers
Experimenting with Reinforcement Learning with Verifiable Re
Nathan Lambert
[Full Workshop] Reinforcement Learning, Kernels, Reasoning,
AI Engineer
torch.accelerator: A Unified, Device-Agnostic Runtime API fo
PyTorch
Larry Ellison Keynote on Oracle's Vision and Strategy: Oracl
Oracle
The AI Scaling Problem
Edan Meyer
Fast LLM Serving with vLLM and PagedAttention
Anyscale
Ex-OpenAI Scientist WARNS: "You Have No Idea What's Coming"
AI Upload
Reinforcement Learning (RL) for LLMs
Natasha Jaques
Denny Zhou: LLM Reasoning: Key Ideas and Limitations
Mayur Naik
Model Context Protocol (MCP), clearly explained (why it matt
Greg Isenberg
Galvatron: An Automatic Distributed Training System for Effi
PyTorch
Stanford CS229 I Machine Learning I Building Large Language
Stanford Online
SGLang: An Efficient Open-Source Framework for Large-Scale L
PyTorch
