NVIDIA / NeMo-RLLinks
Scalable toolkit for efficient model reinforcement
☆361Updated this week
Alternatives and similar repositories for NeMo-RL
Users that are interested in NeMo-RL are comparing it to the libraries listed below
Sorting:
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆249Updated this week
- ☆188Updated 3 months ago
- A project to improve skills of large language models☆413Updated this week
- Super-Efficient RLHF Training of LLMs with Parameter Reallocation☆299Updated last month
- SkyRL-v0: Train Real-World Long-Horizon Agents via Reinforcement Learning☆343Updated last week
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆215Updated 2 months ago
- LLM KV cache compression made easy☆493Updated 3 weeks ago
- 🔥 A minimal training framework for scaling FLA models☆146Updated 3 weeks ago
- Triton-based implementation of Sparse Mixture of Experts.☆216Updated 6 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆203Updated 2 weeks ago
- Ring attention implementation with flash attention☆771Updated last week
- Scalable toolkit for efficient model alignment☆803Updated 2 weeks ago
- Triton implementation of FlashAttention2 that adds Custom Masks.☆117Updated 9 months ago
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆208Updated 9 months ago
- Efficient triton implementation of Native Sparse Attention.☆155Updated last week
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆367Updated this week
- VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework☆339Updated 3 weeks ago
- Async pipelined version of Verl☆91Updated last month
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆333Updated 5 months ago
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆117Updated this week
- Large Context Attention☆711Updated 4 months ago
- kernels, of the mega variety☆184Updated this week
- Explorations into some recent techniques surrounding speculative decoding☆266Updated 5 months ago
- Normalized Transformer (nGPT)☆181Updated 6 months ago
- Efficient LLM Inference over Long Sequences☆376Updated this week
- Zero Bubble Pipeline Parallelism☆395Updated 3 weeks ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆202Updated 6 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆291Updated 6 months ago
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆196Updated this week
- ☆450Updated this week