Alternatives and similar repositories for TransMLA

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

• JT-Ushio / MHA2MLA
  Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs
  ☆197Updated last week
• OpenNLPLab / lightning-attention
  Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models
  ☆338Updated 9 months ago
• QwenLM / ParScale
  Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling
  ☆460Updated 6 months ago
• mit-han-lab / duo-attention
  [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
  ☆510Updated 10 months ago
• NVlabs / Fast-dLLM
  Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"
  ☆725Updated 2 weeks ago
• tensorgi / TPA
  [NeurIPS 2025 Spotlight] TPA: Tensor ProducT ATTenTion Transformer (T6) (https://arxiv.org/abs/2501.06425)
  ☆431Updated last month
• fla-org / native-sparse-attention
  🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"
  ☆938Updated 8 months ago
• fla-org / flame
  🔥 A minimal training framework for scaling FLA models
  ☆319Updated 3 weeks ago
• step-law / steplaw
  ☆208Updated last month
• dhcode-cpp / NSA-pytorch
  DeepSeek Native Sparse Attention pytorch implementation
  ☆109Updated last month
• weigao266 / Awesome-Efficient-Arch
  Speed Always Wins: A Survey on Efficient Architectures for Large Language Models
  ☆370Updated last month
• NVlabs / GatedDeltaNet
  [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule
  ☆388Updated 2 months ago
• pprp / Awesome-Efficient-MoE
  Efficient Mixture of Experts for LLM Paper List
  ☆145Updated 2 months ago
• mdy666 / Qwen-Native-Sparse-Attention
  qwen-nsa
  ☆84Updated last month
• astramind-ai / Mixture-of-depths
  Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"
  ☆176Updated last year
• NVlabs / MaskLLM
  [NeurIPS 24 Spotlight] MaskLLM: Learnable Semi-structured Sparsity for Large Language Models
  ☆182Updated 11 months ago
• NVlabs / COAT
  [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training
  ☆251Updated 4 months ago
• yaof20 / Flash-RL
  Implementation for FP8/INT8 Rollout for RL training without performence drop.
  ☆279Updated last month
• microsoft / SeerAttention
  SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs
  ☆176Updated 2 months ago
• NVIDIA / Star-Attention
  Efficient LLM Inference over Long Sequences
  ☆393Updated 5 months ago
• XunhaoLai / native-sparse-attention-triton
  Efficient triton implementation of Native Sparse Attention.
  ☆254Updated 6 months ago
• NVlabs / Minitron
  A family of compressed models obtained via pruning and knowledge distillation
  ☆359Updated last month
• mit-han-lab / x-attention
  [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring
  ☆255Updated 5 months ago
• lucidrains / native-sparse-attention-pytorch
  Implementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paper
  ☆789Updated 3 months ago
• ZihanWang314 / CoE
  Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models
  ☆224Updated last month
• stepfun-ai / Step3
  ☆439Updated 4 months ago
• RyanLiu112 / compute-optimal-tts
  Official codebase for "Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling".
  ☆277Updated 9 months ago
• thu-nics / MoA
  [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>
  ☆153Updated 2 weeks ago
• GraphPKU / PiSSA
  PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models(NeurIPS 2024 Spotlight)
  ☆403Updated 5 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