JT-Ushio / MHA2MLALinks
Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs
☆181Updated last month
Alternatives and similar repositories for MHA2MLA
Users that are interested in MHA2MLA are comparing it to the libraries listed below
Sorting:
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆417Updated 2 months ago
- TransMLA: Multi-Head Latent Attention Is All You Need☆331Updated 2 weeks ago
- Efficient triton implementation of Native Sparse Attention.☆177Updated 2 months ago
- Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models☆136Updated last year
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆480Updated 5 months ago
- Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models☆217Updated last month
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆167Updated last year
- [ICML 2025] |TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation☆110Updated 2 months ago
- ☆196Updated 3 months ago
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆140Updated 2 weeks ago
- Efficient LLM Inference over Long Sequences☆385Updated last month
- [ICLR2025] Codebase for "ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing", built on Megatron-LM.☆85Updated 7 months ago
- ☆112Updated last month
- Simple extension on vLLM to help you speed up reasoning model without training.☆169Updated 2 months ago
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆320Updated this week
- 🔥 A minimal training framework for scaling FLA models☆209Updated last month
- Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models☆323Updated 5 months ago
- KV cache compression for high-throughput LLM inference☆134Updated 5 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆218Updated last month
- ☆136Updated 5 months ago
- ☆326Updated this week
- ☆77Updated 3 months ago
- ☆123Updated 2 months ago
- A highly capable 2.4B lightweight LLM using only 1T pre-training data with all details.☆200Updated last week
- Block Transformer: Global-to-Local Language Modeling for Fast Inference (NeurIPS 2024)☆160Updated 3 months ago
- Official codebase for "Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling".☆268Updated 5 months ago
- Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?☆112Updated 9 months ago
- qwen-nsa☆69Updated 3 months ago
- OpenSeek aims to unite the global open source community to drive collaborative innovation in algorithms, data and systems to develop next…☆215Updated last month
- Efficient Mixture of Experts for LLM Paper List☆87Updated 7 months ago