NVIDIA-NeMo / RLLinks
Scalable toolkit for efficient model reinforcement
☆1,054Updated this week
Alternatives and similar repositories for RL
Users that are interested in RL are comparing it to the libraries listed below
Sorting:
- ☆917Updated last month
- PyTorch-native post-training at scale☆549Updated last week
- SkyRL: A Modular Full-stack RL Library for LLMs☆1,287Updated last week
- A project to improve skills of large language models☆628Updated this week
- Scalable toolkit for efficient model alignment☆847Updated last month
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆851Updated last week
- slime is an LLM post-training framework for RL Scaling.☆2,612Updated last week
- PyTorch building blocks for the OLMo ecosystem☆482Updated this week
- Async RL Training at Scale☆867Updated this week
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆576Updated last month
- Muon is Scalable for LLM Training☆1,372Updated 4 months ago
- OLMoE: Open Mixture-of-Experts Language Models☆919Updated 2 months ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆928Updated 8 months ago
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,164Updated 3 months ago
- LLM KV cache compression made easy☆701Updated this week
- Ring attention implementation with flash attention☆923Updated 2 months ago
- ☆555Updated 2 months ago
- Super-Efficient RLHF Training of LLMs with Parameter Reallocation☆326Updated 7 months ago
- FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.☆313Updated last month
- HuggingFace conversion and training library for Megatron-based models☆228Updated this week
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆360Updated 11 months ago
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆271Updated last week
- Recipes to scale inference-time compute of open models☆1,118Updated 6 months ago
- ☆224Updated last week
- ☆344Updated this week
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆316Updated last week
- KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA (+ more DSLs)☆683Updated this week
- Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"☆561Updated last month
- Efficient LLM Inference over Long Sequences☆392Updated 5 months ago
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆460Updated 6 months ago