NVlabs / QeRLLinks
QeRL enables RL for 32B LLMs on a single H100 GPU.
☆467Updated 3 weeks ago
Alternatives and similar repositories for QeRL
Users that are interested in QeRL are comparing it to the libraries listed below
Sorting:
- dInfer: An Efficient Inference Framework for Diffusion Language Models☆361Updated last week
- CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning☆275Updated last month
- Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models☆226Updated last month
- PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning☆177Updated last week
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆154Updated 3 weeks ago
- GPU-optimized framework for training diffusion language models at any scale. The backend of Quokka, Super Data Learners, and OpenMoE 2 tr…☆301Updated last month
- [NeurIPS'25 Oral] Query-agnostic KV cache eviction: 3–4× reduction in memory and 2× decrease in latency (Qwen3/2.5, Gemma3, LLaMA3)☆169Updated 3 weeks ago
- ☆107Updated 3 months ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆126Updated 5 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆158Updated 2 months ago
- Official PyTorch implementation for Hogwild! Inference: Parallel LLM Generation with a Concurrent Attention Cache☆136Updated 4 months ago
- Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support☆209Updated this week
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆107Updated last month
- ☆132Updated 6 months ago
- The evaluation framework for training-free sparse attention in LLMs☆106Updated 2 months ago
- Efficient triton implementation of Native Sparse Attention.☆254Updated 6 months ago
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆198Updated 2 weeks ago
- Efficient LLM Inference over Long Sequences☆393Updated 5 months ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆281Updated last month
- ☆207Updated last month
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆256Updated 5 months ago
- Multi-Turn RL Training System with AgentTrainer for Language Model Game Reinforcement Learning☆54Updated last month
- Ring-V2 is a reasoning MoE LLM provided and open-sourced by InclusionAI.☆83Updated last month
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆105Updated 2 weeks ago
- Training-free Post-training Efficient Sub-quadratic Complexity Attention. Implemented with OpenAI Triton.☆148Updated last month
- Code for data-aware compression of DeepSeek models☆66Updated last week
- ☆259Updated 6 months ago
- KV cache compression for high-throughput LLM inference☆148Updated 10 months ago
- ☆88Updated 6 months ago
- Work in progress.☆75Updated 3 weeks ago