aibrix / PrisKVLinks
High Performance KV Cache Store for LLM
☆45Updated last week
Alternatives and similar repositories for PrisKV
Users that are interested in PrisKV are comparing it to the libraries listed below
Sorting:
- A User-Transparent Block Cache Enabling High-Performance Out-of-Core Processing with In-Memory Programs☆76Updated last month
- GeminiFS: A Companion File System for GPUs☆72Updated 11 months ago
- This is the source code for our (Tobias Ziegler, Jacob Nelson-Slivon, Carsten Binnig and Viktor Leis) published paper at SIGMOD’23: Desig…☆28Updated last year
- This is the implementation repository of our OSDI'23 paper: SMART: A High-Performance Adaptive Radix Tree for Disaggregated Memory.☆63Updated last year
- [OSDI 2024] Motor: Enabling Multi-Versioning for Distributed Transactions on Disaggregated Memory☆50Updated last year
- Fast RDMA-based Ordered Key-Value Store using Remote Learned Cache☆117Updated 5 years ago
- RLib is a header-only library for easier usage of RDMA.☆45Updated 4 years ago
- This is the implementation repository of our FAST'23 paper: FUSEE: A Fully Memory-Disaggregated Key-Value Store.☆60Updated 2 years ago
- Accelerating AI Training and Inference from Storage Perspective (Must-read Papers on Storage for AI)☆57Updated last month
- ROLEX: A Scalable RDMA-oriented Learned Key-Value Store for Disaggregated Memory Systems☆80Updated 2 years ago
- This is the implementation repository of our SOSP'24 paper: Aceso: Achieving Efficient Fault Tolerance in Memory-Disaggregated Key-Value …☆22Updated last year
- [SIGMOD '24] CaaS-LSM: Compaction-as-a-Service for LSM-based Key-Value Stores in Storage Disaggregated Infrastructure☆71Updated last year
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆41Updated 8 months ago
- Nova-LSM is a component-based design of the LSM-tree using fast and high bandwidth networks such as RDMA.☆52Updated 4 years ago
- [FAST 2022] FORD: Fast One-sided RDMA-based Distributed Transactions for Disaggregated Persistent Memory☆62Updated last year
- Tiered Indexing is a general approach to improve the memory utilization of buffer-managed data structures including B+tree, Hashing, Heap…☆48Updated 7 months ago
- Viper: A hybrid PMem-DRAM Key-Value Store for Persistent Memory (VLDB '21)☆78Updated 3 years ago
- DINOMO: An Elastic, Scalable, High-Performance Key-Value Store for Disaggregated Persistent Memory (PVLDB 2022, VLDB 2023)☆37Updated 2 years ago
- ☆35Updated 4 years ago
- Sherman: A Write-Optimized Distributed B+Tree Index on Disaggregated Memory☆110Updated last year
- ☆28Updated last year
- Lightning In-Memory Object Store☆47Updated 4 years ago
- Gengar, a distributed shared hybrid memory pool with RDMA support. Gengar allows applications to access remote DRAM/NVM in a large and gl…☆24Updated 3 years ago
- ☆60Updated 2 years ago
- Rcmp: Reconstructing RDMA-based Memory Disaggregation via CXL☆61Updated 2 years ago
- Hydra adds resilience and high availability to remote memory solutions.☆34Updated 3 years ago
- Vector search with bounded performance.☆35Updated 2 years ago
- Optimizing data-intensive systems in disaggregated data centers☆13Updated 3 years ago
- dLSM: An LSM-Based Index for RDMA-Enabled Memory Disaggregation☆36Updated 2 years ago
- The repo for SOSP23 paper: FIFO queues are all you need for cache evictions☆136Updated last year