pku-liang / ArkValeLinks
ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)
☆40Updated 5 months ago
Alternatives and similar repositories for ArkVale
Users that are interested in ArkVale are comparing it to the libraries listed below
Sorting:
- ☆54Updated last year
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆39Updated last month
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆47Updated 2 months ago
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆36Updated last month
- MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN (ASPLOS'24)☆51Updated last year
- ☆14Updated last year
- LLM Inference analyzer for different hardware platforms☆69Updated last week
- ☆62Updated 11 months ago
- Explore Inter-layer Expert Affinity in MoE Model Inference☆9Updated last year
- ☆17Updated 2 months ago
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆25Updated last year
- Code release for AdapMoE accepted by ICCAD 2024☆25Updated last month
- ☆21Updated last year
- ☆99Updated 6 months ago
- ☆146Updated 10 months ago
- 16-fold memory access reduction with nearly no loss☆94Updated 2 months ago
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆41Updated last week
- ☆47Updated last year
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆136Updated 10 months ago
- ☆108Updated last week
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Honorable Mention]☆10Updated 2 months ago
- ☆58Updated last year
- LLM serving cluster simulator☆100Updated last year
- A lightweight design for computation-communication overlap.☆132Updated 3 weeks ago
- Implement some method of LLM KV Cache Sparsity☆32Updated 11 months ago
- Summary of some awesome work for optimizing LLM inference☆73Updated this week
- [SIGMOD 2025] PQCache: Product Quantization-based KVCache for Long Context LLM Inference☆50Updated 4 months ago
- ☆142Updated 11 months ago
- Stateful LLM Serving☆70Updated 2 months ago
- [HPCA'24] Smart-Infinity: Fast Large Language Model Training using Near-Storage Processing on a Real System☆44Updated last year