UNITES-Lab / HEXA-MoELinks
Official code for the paper "HEXA-MoE: Efficient and Heterogeneous-Aware MoE Acceleration with Zero Computation Redundancy"
☆14Updated 3 months ago
Alternatives and similar repositories for HEXA-MoE
Users that are interested in HEXA-MoE are comparing it to the libraries listed below
Sorting:
- Adaptive Attention Sparsity with Hierarchical Top-p Pruning☆17Updated 4 months ago
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆48Updated 3 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆41Updated last month
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆39Updated last year
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆39Updated 2 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆38Updated 10 months ago
- Code release for AdapMoE accepted by ICCAD 2024☆26Updated 2 months ago
- ☆19Updated 9 months ago
- 16-fold memory access reduction with nearly no loss☆99Updated 3 months ago
- An auxiliary project analysis of the characteristics of KV in DiT Attention.☆31Updated 6 months ago
- [COLM 2024] SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models☆20Updated 8 months ago
- ☆19Updated 6 months ago
- ☆49Updated last month
- ☆10Updated 5 months ago
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆40Updated 6 months ago
- SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference☆47Updated 7 months ago
- Quantized Attention on GPU☆44Updated 7 months ago
- [ICLR 2025] DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference☆24Updated last week
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆49Updated 2 weeks ago
- ☆14Updated last year
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆54Updated 2 weeks ago
- Implementation for the paper: CMoE: Fast Carving of Mixture-of-Experts for Efficient LLM Inference☆21Updated 3 months ago
- ☆77Updated 2 months ago
- Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its…☆22Updated 9 months ago
- Estimate MFU for DeepSeekV3☆24Updated 5 months ago
- LLM Inference with Microscaling Format☆23Updated 7 months ago
- ☆60Updated 2 months ago
- XAttention: Block Sparse Attention with Antidiagonal Scoring☆166Updated this week
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆48Updated 7 months ago
- ☆54Updated last year