NVIDIA-NeMo / RLLinks
Scalable toolkit for efficient model reinforcement
☆438Updated this week
Alternatives and similar repositories for RL
Users that are interested in 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…☆253Updated this week
- Scalable toolkit for efficient model alignment☆814Updated 3 weeks ago
- SkyRL-v0: Train Real-World Long-Horizon Agents via Reinforcement Learning☆410Updated last week
- ☆193Updated 4 months ago
- VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework☆353Updated last month
- LLM KV cache compression made easy☆508Updated this week
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆219Updated 2 months ago
- Ring attention implementation with flash attention☆782Updated last week
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆465Updated 4 months ago
- slime is a LLM post-training framework aiming at scaling RL.☆328Updated this week
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆379Updated last week
- Super-Efficient RLHF Training of LLMs with Parameter Reallocation☆303Updated last month
- Efficient LLM Inference over Long Sequences☆377Updated 2 weeks ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆209Updated this week
- A project to improve skills of large language models☆423Updated this week
- Explorations into some recent techniques surrounding speculative decoding☆268Updated 5 months ago
- 🔥 A minimal training framework for scaling FLA models☆170Updated last week
- ☆471Updated last week
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆210Updated 10 months ago
- Async pipelined version of Verl☆100Updated 2 months ago
- Efficient triton implementation of Native Sparse Attention.☆167Updated 3 weeks ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆295Updated 6 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆519Updated 3 weeks ago
- KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA problems☆415Updated 2 weeks ago
- Triton-based implementation of Sparse Mixture of Experts.☆217Updated 6 months ago
- Megatron's multi-modal data loader☆213Updated last week
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆277Updated 2 months ago
- Zero Bubble Pipeline Parallelism☆398Updated last month
- A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).☆255Updated this week
- Large Context Attention☆716Updated 4 months ago