Alternatives and similar repositories for MoA:

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

• FasterDecoding / TEAL
  ☆126Updated 2 months ago
• opengear-project / GEAR
  GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM
  ☆161Updated 9 months ago
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆91Updated last month
• ByteDance-Seed / FlexPrefill
  Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
  ☆100Updated 2 weeks ago
• mit-han-lab / Quest
  [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
  ☆274Updated 5 months ago
• microsoft / SeerAttention
  SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs
  ☆97Updated this week
• Lucky-Lance / Expert_Sparsity
  [ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models
  ☆88Updated 11 months ago
• mit-han-lab / Block-Sparse-Attention
  A sparse attention kernel supporting mix sparse patterns
  ☆200Updated 2 months ago
• mit-han-lab / x-attention
  XAttention: Block Sparse Attention with Antidiagonal Scoring
  ☆142Updated last month
• NVlabs / COAT
  [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training
  ☆189Updated 2 weeks ago
• FasterDecoding / SnapKV
  ☆238Updated last year
• hahnyuan / ASVD4LLM
  Activation-aware Singular Value Decomposition for Compressing Large Language Models
  ☆66Updated 6 months ago
• XunhaoLai / native-sparse-attention-triton
  Efficient triton implementation of Native Sparse Attention.
  ☆142Updated 3 weeks ago
• thu-ml / ReMoE
  [ICLR2025] Codebase for "ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing", built on Megatron-LM.
  ☆70Updated 4 months ago
• pprp / Pruner-Zero
  Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMs
  ☆81Updated 5 months ago
• ChenMnZ / PrefixQuant
  An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization
  ☆129Updated 3 months ago
• NVlabs / MaskLLM
  [NeurIPS 24 Spotlight] MaskLLM: Learnable Semi-structured Sparsity for Large Language Models
  ☆162Updated 4 months ago
• htqin / IR-QLoRA
  [ICML 2024 Oral] This project is the official implementation of our Accurate LoRA-Finetuning Quantization of LLMs via Information Retenti…
  ☆65Updated last year
• sramshetty / mixture-of-depths
  An unofficial implementation of "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"
  ☆35Updated 10 months ago
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆115Updated 5 months ago
• hetailang / SqueezeAttention
  ☆37Updated 6 months ago
• mit-han-lab / duo-attention
  [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
  ☆456Updated 2 months ago
• shadowpa0327 / Palu
  [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection
  ☆103Updated 2 months ago
• jy-yuan / KIVI
  [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
  ☆293Updated 3 months ago
• CASE-Lab-UMD / Unified-MoE-Compression
  The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".
  ☆66Updated last month
• OpenSparseLLMs / Linear-MoE
  ☆80Updated 3 weeks ago
• UNITES-Lab / MC-SMoE
  [ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"
  ☆82Updated 11 months ago
• thu-nics / qllm-eval
  Code Repository of Evaluating Quantized Large Language Models
  ☆122Updated 7 months ago
• astramind-ai / Mixture-of-depths
  Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"
  ☆158Updated 10 months ago
• Equationliu / Kangaroo
  [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…
  ☆54Updated 10 months ago