NVIDIA-NeMo / RLLinks
Scalable toolkit for efficient model reinforcement
☆558Updated this week
Alternatives and similar repositories for RL
Users that are interested in RL are comparing it to the libraries listed below
Sorting:
- A project to improve skills of large language models☆490Updated this week
- Scalable toolkit for efficient model alignment☆833Updated this week
- SkyRL: A Modular Full-stack RL Library for LLMs☆651Updated this week
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆258Updated last week
- LLM KV cache compression made easy☆560Updated this week
- ☆203Updated 5 months ago
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆418Updated this week
- slime is a LLM post-training framework aiming for RL Scaling.☆975Updated this week
- Efficient LLM Inference over Long Sequences☆385Updated last month
- Ring attention implementation with flash attention☆828Updated last week
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆342Updated 7 months ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆731Updated 4 months ago
- Explorations into some recent techniques surrounding speculative decoding☆275Updated 7 months ago
- Super-Efficient RLHF Training of LLMs with Parameter Reallocation☆305Updated 3 months ago
- ☆506Updated this week
- PyTorch building blocks for the OLMo ecosystem☆267Updated this week
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆480Updated 5 months ago
- Large Context Attention☆719Updated 6 months ago
- [ICML 2024] CLLMs: Consistency Large Language Models☆397Updated 8 months ago
- Megatron's multi-modal data loader☆230Updated last week
- 🔥 A minimal training framework for scaling FLA models☆209Updated last month
- An extension of the nanoGPT repository for training small MOE models.☆163Updated 4 months ago
- Decentralized RL Training at Scale☆400Updated this week
- Triton-based implementation of Sparse Mixture of Experts.☆227Updated 8 months ago
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆226Updated 3 weeks ago
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆417Updated 2 months ago
- KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA problems☆493Updated last week
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆532Updated 2 months ago
- VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework☆395Updated last week
- Reproducible, flexible LLM evaluations☆226Updated 3 weeks ago