NVIDIA-NeMo / RLLinks
Scalable toolkit for efficient model reinforcement
☆956Updated this week
Alternatives and similar repositories for RL
Users that are interested in RL are comparing it to the libraries listed below
Sorting:
- ☆843Updated last week
- A project to improve skills of large language models☆587Updated this week
- SkyRL: A Modular Full-stack RL Library for LLMs☆1,060Updated last week
- Scalable toolkit for efficient model alignment☆841Updated 2 weeks ago
- slime is an LLM post-training framework for RL Scaling.☆2,232Updated this week
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆775Updated this week
- OLMoE: Open Mixture-of-Experts Language Models☆888Updated last month
- Ring attention implementation with flash attention☆903Updated last month
- LLM KV cache compression made easy☆660Updated last week
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆270Updated 3 months ago
- ☆543Updated last month
- Async RL Training at Scale☆722Updated this week
- Muon is Scalable for LLM Training☆1,336Updated 2 months ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆903Updated 7 months ago
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,126Updated last month
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆539Updated this week
- ☆222Updated 3 weeks ago
- Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"☆538Updated 2 weeks ago
- Super-Efficient RLHF Training of LLMs with Parameter Reallocation☆323Updated 6 months ago
- FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.☆296Updated 2 months ago
- Efficient LLM Inference over Long Sequences☆390Updated 4 months ago
- Post-training with Tinker☆1,096Updated this week
- KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA problems☆612Updated 2 weeks ago
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆342Updated 10 months ago
- PyTorch-native post-training at scale☆83Updated last week
- Recipes to scale inference-time compute of open models☆1,111Updated 5 months ago
- PyTorch building blocks for the OLMo ecosystem☆307Updated last week
- Large Context Attention☆746Updated last week
- Minimalistic large language model 3D-parallelism training☆2,267Updated last month
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆448Updated 5 months ago