Alternatives and similar repositories for MHA2MLA

Users that are interested in MHA2MLA are comparing it to the libraries listed below

• QwenLM / ParScale
  Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling
  ☆456Updated 6 months ago
• MuLabPKU / TransMLA
  TransMLA: Multi-Head Latent Attention Is All You Need (NeurIPS 2025 Spotlight)
  ☆413Updated 2 months ago
• step-law / steplaw
  ☆207Updated last month
• NVlabs / COAT
  [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training
  ☆250Updated 3 months ago
• mit-han-lab / duo-attention
  [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
  ☆507Updated 9 months ago
• SkyworkAI / Skywork-MoE
  Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models
  ☆137Updated last year
• yaof20 / Flash-RL
  Implementation for FP8/INT8 Rollout for RL training without performence drop.
  ☆275Updated 3 weeks ago
• stepfun-ai / Step3
  ☆439Updated 3 months ago
• bigai-nlco / TokenSwift
  [ICML 2025] |TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation
  ☆118Updated 6 months ago
• OpenNLPLab / lightning-attention
  Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models
  ☆335Updated 9 months ago
• XunhaoLai / native-sparse-attention-triton
  Efficient triton implementation of Native Sparse Attention.
  ☆251Updated 6 months ago
• thu-ml / ReMoE
  [ICLR2025] Codebase for "ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing", built on Megatron-LM.
  ☆99Updated 11 months ago
• OpenSparseLLMs / Linear-MoE
  ☆120Updated 5 months ago
• ZihanWang314 / CoE
  Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models
  ☆223Updated 3 weeks ago
• weigao266 / Awesome-Efficient-Arch
  Speed Always Wins: A Survey on Efficient Architectures for Large Language Models
  ☆368Updated 3 weeks ago
• microsoft / SeerAttention
  SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs
  ☆175Updated 2 months ago
• Tencent / AngelSlim
  Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.
  ☆212Updated this week
• hao-ai-lab / Dynasor
  [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.
  ☆209Updated 6 months ago
• astramind-ai / Mixture-of-depths
  Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"
  ☆175Updated last year
• NVlabs / Fast-dLLM
  Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"
  ☆713Updated this week
• inclusionAI / Ling-V2
  Ling-V2 is a MoE LLM provided and open-sourced by InclusionAI.
  ☆237Updated last month
• NVIDIA-NeMo / Megatron-Bridge
  HuggingFace conversion and training library for Megatron-based models
  ☆228Updated this week
• jshuadvd / LongRoPE
  Implementation of the LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens Paper
  ☆152Updated last year
• RUC-GSAI / YuLan-Mini
  A highly capable 2.4B lightweight LLM using only 1T pre-training data with all details.
  ☆222Updated 4 months ago
• NVIDIA / Star-Attention
  Efficient LLM Inference over Long Sequences
  ☆392Updated 5 months ago
• Dao-AILab / grouped-latent-attention
  ☆132Updated 6 months ago
• fla-org / flame
  🔥 A minimal training framework for scaling FLA models
  ☆311Updated 2 weeks ago
• FasterDecoding / SnapKV
  ☆290Updated 4 months ago
• mdy666 / Qwen-Native-Sparse-Attention
  qwen-nsa
  ☆84Updated last month
• MiroMindAI / MiroRL
  MiroRL is an MCP-first reinforcement learning framework for deep research agent.
  ☆180Updated 3 months ago