NVlabs / QeRLLinks
QeRL enables RL for 32B LLMs on a single H100 GPU.
☆477Updated 2 months ago
Alternatives and similar repositories for QeRL
Users that are interested in QeRL are comparing it to the libraries listed below
Sorting:
- Block Diffusion for Ultra-Fast Speculative Decoding☆432Updated last week
- dInfer: An Efficient Inference Framework for Diffusion Language Models☆403Updated 3 weeks ago
- CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning☆285Updated 2 months ago
- ☆133Updated 8 months ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆128Updated 7 months ago
- Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models☆227Updated 2 months ago
- Efficient triton implementation of Native Sparse Attention.☆261Updated 8 months ago
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆154Updated 2 weeks ago
- ☆110Updated 4 months ago
- ☆220Updated 2 months ago
- [NeurIPS'25 Oral] Query-agnostic KV cache eviction: 3–4× reduction in memory and 2× decrease in latency (Qwen3/2.5, Gemma3, LLaMA3)☆193Updated last week
- The evaluation framework for training-free sparse attention in LLMs☆110Updated 3 months ago
- Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support☆259Updated this week
- GPU-optimized framework for training diffusion language models at any scale. The backend of Quokka, Super Data Learners, and OpenMoE 2 tr…☆318Updated 2 months ago
- Official PyTorch implementation for Hogwild! Inference: Parallel LLM Generation with a Concurrent Attention Cache☆140Updated 5 months ago
- Spectral Sphere Optimizer☆90Updated 2 weeks ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆288Updated 2 months ago
- PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning☆292Updated 2 weeks ago
- Training-free Post-training Efficient Sub-quadratic Complexity Attention. Implemented with OpenAI Triton.☆148Updated 2 months ago
- Multi-Turn RL Training System with AgentTrainer for Language Model Game Reinforcement Learning☆58Updated last month
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆203Updated last month
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆161Updated 3 months ago
- [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.☆218Updated 8 months ago
- KV cache compression for high-throughput LLM inference☆150Updated 11 months ago
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆115Updated 2 months ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆521Updated 11 months ago
- Efficient LLM Inference over Long Sequences☆394Updated 7 months ago
- Official JAX implementation of End-to-End Test-Time Training for Long Context☆478Updated last week
- mHC kernels implemented in CUDA☆233Updated 2 weeks ago
- [NeurIPS 24 Spotlight] MaskLLM: Learnable Semi-structured Sparsity for Large Language Models☆183Updated last year