Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]
☆12Nov 8, 2024Updated 2 years ago
Alternatives and similar repositories for 25ASPLOS-Medusa
Users that are interested in 25ASPLOS-Medusa are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆50May 13, 2025Updated last year
- Integrated Training Platform (ITP) traces used in ElasticFlow paper.☆30Dec 23, 2022Updated 3 years ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆56May 10, 2024Updated 2 years ago
- Injecting Adrenaline into LLM Serving: Boosting Resource Utilization and Throughput via Attention Disaggregation☆43Oct 26, 2026Updated 3 weeks ago
- ☆13Sep 8, 2021Updated 5 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- codes and plots for "Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs"☆11Dec 30, 2024Updated last year
- ☆11Nov 14, 2023Updated 3 years ago
- ☆10Nov 22, 2024Updated last year
- Artifacts for SWARM: Replicating Shared Disaggregated-Memory Data in No Time☆10Sep 25, 2024Updated 2 years ago
- 🤖 A streamlined, easy‑to‑install implementation of Fourier Neural Operators for time‑dependent and cloud‑point learning tasks.☆10May 28, 2023Updated 3 years ago
- A DSL for Stencil Codes☆14Nov 27, 2024Updated last year
- Anonymous Chatting Website implemented by WebSocket(匿名在线聊天交友网站)☆16Sep 17, 2015Updated 11 years ago
- We present a set of all-reduce compatible gradient compression algorithms which significantly reduce the communication overhead while mai…☆10Nov 14, 2021Updated 5 years ago
- 本文译自 University of Edinburgh 的 Volker Seeker 的 Process Scheduling in Linux , 介绍了 Linux 3.1 的任务调度机制。☆11Aug 11, 2016Updated 10 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆21Aug 27, 2016Updated 10 years ago
- [ASPLOS'24] FaaSMem: Improving Memory Efficiency of Serverless Computing with Memory Pool Architecture☆13Nov 4, 2024Updated 2 years ago
- [ISCA'25] LIA: A Single-GPU LLM Inference Acceleration with Cooperative AMX-Enabled CPU-GPU Computation and CXL Offloading☆27Jan 6, 2026Updated 10 months ago
- A fault-tolerant RDMA-based disaggregated key-value store with 1-RTT UPDATEs and GETs thanks to the SWARM replication protocol☆14Sep 25, 2024Updated 2 years ago
- 数据库案例:1.使用时间和日期函数,增,查时间字段。2.利用ContentProvider,CursorLoader,SQLite实现数据库的观察者模式。3.RxJava,SQLBrite实现数据库的观察者模式。4.拷贝外部db文件到数据库中☆21May 11, 2017Updated 9 years ago
- ☆10Sep 14, 2023Updated 3 years ago
- An efficient service for transparent GPU multiplexing with VRAM oversubscription, OSDI '26☆14Sep 24, 2026Updated last month
- Dataset and pre-trained model of EMNLP-IJCNLP 2019 paper "TalkDown: A Corpus for Condescension Detection in Context."☆10Jan 26, 2020Updated 6 years ago
- DiscreteTom's Blog Boilerplate.☆10Mar 6, 2023Updated 3 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- This is the final project of 2020 DBMS course in SYSU☆10Jun 23, 2020Updated 6 years ago
- The official implementation of OSDI'25 paper BlitzScale☆50Apr 15, 2026Updated 7 months ago
- ☆19Updated this week
- 该六子棋程序使用Java语言编写,内置AI落子,主要由阿尔法贝塔搜索+评估函数实现,存在一定的bug,智能方面还行吧☆12Jul 24, 2021Updated 5 years ago
- ☆12Nov 26, 2024Updated last year
- An implementation of Raft Consensus Algorithm in Elixir☆21Apr 3, 2016Updated 10 years ago
- DRAM/SSD hybrid caching system☆15Mar 13, 2025Updated last year
- PAROAttn based on SAGEAttn☆11Nov 30, 2025Updated 11 months ago
- ☆10Apr 5, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Linux kernel SGX driver for Graphene☆12Nov 3, 2020Updated 6 years ago
- Deduplication over dis-aggregated memory for Serverless Computing☆14Mar 21, 2022Updated 4 years ago
- ☆12Mar 22, 2022Updated 4 years ago
- a simple API to use CUPTI☆10Aug 19, 2025Updated last year
- Engine-Agnostic Model Hot-Swapping for Cost-Effective LLM Inference☆15Nov 13, 2025Updated last year
- ☆15Updated this week
- A lightweight CuTe-based CUDA kernel for DuoAttention, optimized for large language model inference.☆12Dec 25, 2025Updated 10 months ago
Are these results useful?