pprp / Awesome-Efficient-MoELinks
Efficient Mixture of Experts for LLM Paper List
☆131Updated last week
Alternatives and similar repositories for Awesome-Efficient-MoE
Users that are interested in Awesome-Efficient-MoE are comparing it to the libraries listed below
Sorting:
- qwen-nsa☆75Updated 5 months ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆117Updated 5 months ago
- D^2-MoE: Delta Decompression for MoE-based LLMs Compression☆67Updated 6 months ago
- The Official Implementation of Ada-KV [NeurIPS 2025]☆99Updated last week
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆60Updated last year
- ☆119Updated 3 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆241Updated last month
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆143Updated 4 months ago
- ☆144Updated 3 months ago
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆234Updated 2 months ago
- ☆280Updated 2 months ago
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆155Updated last week
- [ICML 2025 Oral] Mixture of Lookup Experts☆51Updated 4 months ago
- Official Repo for SparseLLM: Global Pruning of LLMs (NeurIPS 2024)☆66Updated 6 months ago
- Source code for the paper "LongGenBench: Long-context Generation Benchmark"☆22Updated 11 months ago
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆52Updated last year
- Inference Code for Paper "Harder Tasks Need More Experts: Dynamic Routing in MoE Models"☆64Updated last year
- ☆45Updated 10 months ago
- Official implementation of ICML 2024 paper "ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking".☆48Updated last year
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆249Updated last week
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆146Updated 2 months ago
- Due to the huge vocaburary size (151,936) of Qwen models, the Embedding and LM Head weights are excessively heavy. Therefore, this projec…☆27Updated last year
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆202Updated 7 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆168Updated last year
- [ICLR 2025] Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models☆136Updated 2 months ago
- 青稞Talk☆148Updated 2 weeks ago
- 16-fold memory access reduction with nearly no loss☆105Updated 6 months ago
- [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling☆44Updated 2 months ago
- [ACL 2024] Official PyTorch implementation of "IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact"☆47Updated last year
- ☆56Updated last year