Bringing Multi-Head Latent Attention to pretrained LLMs and VLMs: MHA2MLA (ACL 2025), MHA2MLA-VLM (AAAI 2026), and MLAfication.
☆216Oct 25, 2026Updated 3 weeks ago
Alternatives and similar repositories for MLAfication
Users that are interested in MLAfication are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Design hardware-friendly model architectures and migrate existing LLMs with minimal performance loss☆520Nov 11, 2026Updated last week
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆1,029Feb 5, 2026Updated 9 months ago
- Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models☆346Feb 23, 2025Updated last year
- Efficient triton implementation of Native Sparse Attention.☆286May 23, 2025Updated last year
- Odysseus: Playground of LLM Sequence Parallelism☆83Jun 17, 2024Updated 2 years ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆172Oct 13, 2025Updated last year
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆135Jun 24, 2025Updated last year
- ☆139May 29, 2025Updated last year
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆55Oct 18, 2024Updated 2 years ago
- Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models☆142Jun 12, 2024Updated 2 years ago
- MoBA: Mixture of Block Attention for Long-Context LLMs☆2,199Apr 3, 2025Updated last year
- ☆156Mar 4, 2025Updated last year
- FlashMLA: Efficient Multi-head Latent Attention Kernels☆13,278Oct 27, 2026Updated 3 weeks ago
- Fork of Flame repo for training of some new stuff in development☆20Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Block Transformer: Global-to-Local Language Modeling for Fast Inference (NeurIPS 2024)☆166Apr 13, 2025Updated last year
- Muon is Scalable for LLM Training☆1,562Aug 3, 2025Updated last year
- [ICLR 2025] 🧬 RegMix: Data Mixture as Regression for Language Model Pre-training (Spotlight)☆220Feb 17, 2025Updated last year
- CutDiffusion: A Simple, Fast, Cheap, and Strong Diffusion Extrapolation Method☆27Oct 9, 2025Updated last year
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆156Apr 7, 2025Updated last year
- Codes for the paper "BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping…☆96Jan 29, 2026Updated 9 months ago
- qwen-nsa☆87Oct 14, 2025Updated last year
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆186Jul 12, 2024Updated 2 years ago
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,231Updated this week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- [ICCV2025] "Di[M]O: Distilling Masked Diffusion Models into One-step Generator", Yuanzhi Zhu, Xi Wang, Stéphane Lathuilière, Vicky Kal…☆39Aug 14, 2025Updated last year
- ☆104Feb 11, 2026Updated 9 months ago
- 🚀 Efficient implementations for emerging model architectures☆6,059Updated this week
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆643Mar 4, 2024Updated 2 years ago
- Accelerating MoE with IO and Tile-aware Optimizations☆791Aug 29, 2026Updated 2 months ago
- code for Scaling Laws of RoPE-based Extrapolation☆73Oct 16, 2023Updated 3 years ago
- Scaling RL on advanced reasoning models☆698Oct 20, 2025Updated last year
- [NeurIPS 2025] HoPE: Hybrid of Position Embedding for Long Context Vision-Language Models☆30Feb 19, 2026Updated 9 months ago
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆187Feb 27, 2026Updated 8 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆697Sep 16, 2026Updated 2 months ago
- ☆51Jul 3, 2026Updated 4 months ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆545Feb 10, 2025Updated last year
- Rectified Rotary Position Embeddings☆399May 20, 2024Updated 2 years ago
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.☆1,268Feb 25, 2026Updated 8 months ago
- Official Repo for Open-Reasoner-Zero☆2,102Jun 2, 2025Updated last year
- ☆11Sep 9, 2026Updated 2 months ago
Are these results useful?