JT-Ushio / MHA2MLALinks
Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs
☆188Updated 2 months ago
Alternatives and similar repositories for MHA2MLA
Users that are interested in MHA2MLA are comparing it to the libraries listed below
Sorting:
- TransMLA: Multi-Head Latent Attention Is All You Need☆353Updated last week
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆438Updated 3 months ago
- Efficient triton implementation of Native Sparse Attention.☆215Updated 3 months ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆490Updated 7 months ago
- Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models☆136Updated last year
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆436Updated this week
- Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models☆220Updated this week
- Simple extension on vLLM to help you speed up reasoning model without training.☆188Updated 3 months ago
- [ICML 2025] |TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation☆113Updated 3 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆236Updated last month
- ☆198Updated 4 months ago
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆151Updated last month
- Efficient LLM Inference over Long Sequences☆391Updated 2 months ago
- ☆118Updated 3 months ago
- qwen-nsa☆74Updated 5 months ago
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆170Updated last year
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆187Updated last week
- [ICLR2025] Codebase for "ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing", built on Megatron-LM.☆89Updated 8 months ago
- Tina: Tiny Reasoning Models via LoRA☆281Updated 3 weeks ago
- 🔥 A minimal training framework for scaling FLA models☆236Updated 3 weeks ago
- Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme☆139Updated 5 months ago
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆146Updated 2 months ago
- Block Transformer: Global-to-Local Language Modeling for Fast Inference (NeurIPS 2024)☆161Updated 4 months ago
- siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems☆185Updated this week
- A highly capable 2.4B lightweight LLM using only 1T pre-training data with all details.☆211Updated last month
- Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models☆326Updated 6 months ago
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆68Updated 2 weeks ago
- LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.☆248Updated last year
- [ICML'24] The official implementation of “Rethinking Optimization and Architecture for Tiny Language Models”☆123Updated 7 months ago
- MiroRL is an MCP-first reinforcement learning framework for deep research agent.☆151Updated 2 weeks ago