NVIDIA-NeMo / RLLinks
Scalable toolkit for efficient model reinforcement
☆1,024Updated this week
Alternatives and similar repositories for RL
Users that are interested in RL are comparing it to the libraries listed below
Sorting:
- SkyRL: A Modular Full-stack RL Library for LLMs☆1,170Updated this week
- ☆894Updated last week
- A project to improve skills of large language models☆608Updated this week
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆820Updated this week
- Scalable toolkit for efficient model alignment☆844Updated last month
- PyTorch-native post-training at scale☆509Updated this week
- slime is an LLM post-training framework for RL Scaling.☆2,407Updated last week
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆564Updated 2 weeks ago
- LLM KV cache compression made easy☆680Updated this week
- Async RL Training at Scale☆749Updated last week
- OLMoE: Open Mixture-of-Experts Language Models☆901Updated last month
- KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA (+ more DSLs)☆655Updated this week
- Ring attention implementation with flash attention☆906Updated 2 months ago
- Muon is Scalable for LLM Training☆1,354Updated 3 months ago
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,148Updated 2 months ago
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆271Updated last week
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆920Updated 7 months ago
- Post-training with Tinker☆1,932Updated this week
- ☆225Updated 3 weeks ago
- ☆545Updated last month
- Super-Efficient RLHF Training of LLMs with Parameter Reallocation☆322Updated 6 months ago
- Minimalistic large language model 3D-parallelism training☆2,311Updated 2 months ago
- Recipes to scale inference-time compute of open models☆1,117Updated 5 months ago
- [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards☆1,214Updated last month
- PyTorch building blocks for the OLMo ecosystem☆317Updated this week
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆355Updated 11 months ago
- Minimalistic 4D-parallelism distributed training framework for education purpose☆1,892Updated 2 months ago
- ☆995Updated 4 months ago
- Efficient LLM Inference over Long Sequences☆390Updated 4 months ago
- Training library for Megatron-based models☆174Updated this week