NVlabs / QeRLLinks
QeRL enables RL for 32B LLMs on a single H100 GPU.
☆481Updated 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☆459Updated last week
- dInfer: An Efficient Inference Framework for Diffusion Language Models☆410Updated last month
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆155Updated 3 weeks ago
- Efficient triton implementation of Native Sparse Attention.☆262Updated 8 months ago
- Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support☆288Updated this week
- CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning☆287Updated 3 months ago
- ☆131Updated 8 months ago
- mHC kernels implemented in CUDA☆249Updated 3 weeks ago
- ☆111Updated 4 months ago
- ☆119Updated last month
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆128Updated 7 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)☆196Updated 3 weeks ago
- ☆221Updated 2 months ago
- Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models☆228Updated 3 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆160Updated 3 months ago
- GPU-optimized framework for training diffusion language models at any scale. The backend of Quokka, Super Data Learners, and OpenMoE 2 tr…☆321Updated 3 months ago
- Code for data-aware compression of DeepSeek models☆70Updated 2 months ago
- Official PyTorch implementation for Hogwild! Inference: Parallel LLM Generation with a Concurrent Attention Cache☆140Updated 5 months ago
- The evaluation framework for training-free sparse attention in LLMs☆117Updated 2 weeks ago
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆204Updated 2 months ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆289Updated 3 months ago
- Spectral Sphere Optimizer☆94Updated 3 weeks ago
- Training-free Post-training Efficient Sub-quadratic Complexity Attention. Implemented with OpenAI Triton.☆148Updated 3 months ago
- implementations and experimentation on mHC by deepseek - https://arxiv.org/abs/2512.24880☆290Updated this week
- LLaDA2.0 is the diffusion language model series developed by InclusionAI team, Ant Group.☆240Updated last month
- Ring-V2 is a reasoning MoE LLM provided and open-sourced by InclusionAI.☆90Updated 3 months ago
- A curated list of recent papers on efficient video attention for video diffusion models, including sparsification, quantization, and cach…☆55Updated 3 months ago
- [NeurIPS 24 Spotlight] MaskLLM: Learnable Semi-structured Sparsity for Large Language Models☆187Updated last year
- KV cache compression for high-throughput LLM inference☆153Updated last year
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆825Updated 2 weeks ago