thu-nics / MoALinks
[CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>
☆150Updated 4 months ago
Alternatives and similar repositories for MoA
Users that are interested in MoA are comparing it to the libraries listed below
Sorting:
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆152Updated last month
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆245Updated 4 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆169Updated last year
- [ICML24] Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMs☆95Updated 11 months ago
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆169Updated last month
- 16-fold memory access reduction with nearly no loss☆106Updated 7 months ago
- [ICLR‘24 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆97Updated 4 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆245Updated 3 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆41Updated last year
- ☆147Updated 9 months ago
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆80Updated last year
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆80Updated 7 months ago
- [NeurIPS 24 Spotlight] MaskLLM: Learnable Semi-structured Sparsity for Large Language Models☆179Updated 10 months ago
- [ICML 2025] SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models☆45Updated last year
- ☆120Updated 5 months ago
- [ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models☆109Updated last year
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆164Updated 2 weeks ago
- [ICML 2025] SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity☆60Updated 4 months ago
- ☆130Updated 5 months ago
- Official PyTorch implementation of the paper "dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching" (dLLM-Cache…☆176Updated 2 months ago
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆47Updated last year
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆499Updated 9 months ago
- HALO: Hadamard-Assisted Low-Precision Optimization and Training method for finetuning LLMs. 🚀 The official implementation of https://arx…☆28Updated 8 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆131Updated 11 months ago
- Efficient triton implementation of Native Sparse Attention.☆247Updated 5 months ago
- [ICLR2025] Codebase for "ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing", built on Megatron-LM.☆98Updated 10 months ago
- An unofficial implementation of "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆36Updated last year
- ☆287Updated 4 months ago
- ☆61Updated 4 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆346Updated 4 months ago