Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]
☆50May 13, 2025Updated last year
Alternatives and similar repositories for Medusa
Users that are interested in 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]☆12Nov 8, 2024Updated last year
- The official implementation of OSDI'25 paper BlitzScale☆50Apr 15, 2026Updated 6 months ago
- code repo for GCR [FAST'26]☆18Mar 3, 2026Updated 8 months ago
- Fast OS-level support for GPU checkpoint and restore☆298Sep 28, 2025Updated last year
- ☆11Oct 29, 2026Updated last week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- The repository for ATC'25 paper "Greyhound: Hunting Fail-Slows in Hybrid-Parallel Training at Scale"☆18Sep 7, 2026Updated last month
- Deduplication over dis-aggregated memory for Serverless Computing☆14Mar 21, 2022Updated 4 years ago
- ☆21May 11, 2026Updated 5 months ago
- An efficient service for transparent GPU multiplexing with VRAM oversubscription, OSDI '26☆12Sep 24, 2026Updated last month
- [FAST'25] ShiftLock: Mitigate One-sided RDMA Lock Contention via Handover.☆20Feb 11, 2025Updated last year
- [NSDI'26] PolyRL is a reinforcement learning framework for LLM that harvest spot instances on the cloud to reduce cost.☆19Mar 30, 2026Updated 7 months ago
- Resource Multiplexing in Tuning and Serving Large Language Models (USENIX ATC 2025)☆10Apr 21, 2026Updated 6 months ago
- Foundry materializes CUDA graphs along with its execution context to disk to support fast cold start of serving engines.☆68Updated this week
- BlitzScale Router - Distributed LLM Inference Router (Rust)☆17May 25, 2026Updated 5 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Artifacts for SWARM: Replicating Shared Disaggregated-Memory Data in No Time☆10Sep 25, 2024Updated 2 years ago
- ☆186Apr 23, 2026Updated 6 months ago
- ☆19May 28, 2024Updated 2 years ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆526Aug 24, 2026Updated 2 months ago
- ☆19Sep 21, 2025Updated last year
- The source code of INFless，a native serverless platform for AI inference.☆47Oct 10, 2022Updated 4 years ago
- Engine-Agnostic Model Hot-Swapping for Cost-Effective LLM Inference☆15Nov 13, 2025Updated 11 months ago
- Open-source repository for the paper "DyTIS: A Dynamic Dataset Targeted Index Structure Simultaneously Efficient for Search, Insert, and …☆14May 16, 2023Updated 3 years ago
- Examples of usage for Mellanox HW offloads☆17Jan 18, 2022Updated 4 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Research prototype of PRISM — a cost-efficient multi-LLM serving system with flexible time- and space-based GPU sharing.☆77Mar 17, 2026Updated 7 months ago
- [OSDI 2024] Motor: Enabling Multi-Versioning for Distributed Transactions on Disaggregated Memory☆50Mar 3, 2024Updated 2 years ago
- This is the implementation repository of our SOSP'24 paper: Aceso: Achieving Efficient Fault Tolerance in Memory-Disaggregated Key-Value …☆24Oct 20, 2024Updated 2 years ago
- ☆24May 27, 2025Updated last year
- A lightweight CuTe-based CUDA kernel for DuoAttention, optimized for large language model inference.☆12Dec 25, 2025Updated 10 months ago
- Mini-SGLang is a mini version of SGLang project ().☆13Sep 24, 2025Updated last year
- Virtual Decoupled Cores: Composable Programming Framework and Runtime for Async GPUs☆25Oct 27, 2026Updated last week
- Serverless LLM Serving for Everyone.☆717Sep 4, 2026Updated 2 months ago
- ☆11Aug 9, 2021Updated 5 years ago
- 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.
- Deft: A Scalable Tree Index for Disaggregated Memory☆22Apr 23, 2025Updated last year
- Deferred Continuous Batching in Resource-Efficient Large Language Model Serving (EuroMLSys 2024)☆20May 28, 2024Updated 2 years ago
- Code for reproducing results for SOSP paper Bagpipe☆12Oct 20, 2023Updated 3 years ago
- Code repository for the SOSP'25 paper DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelism.☆23Nov 28, 2025Updated 11 months ago
- Source code for "DiLOS: Do Not Trade Compatibility for Performance in Memory Disaggregation (EuroSys'23)"☆21May 15, 2023Updated 3 years ago
- An Implementation for Single-node Big Key-value Cache designed for operating on All-flash-array (AFA)☆10Mar 7, 2023Updated 3 years ago
- A fully serverless implementation of the ZooKeeper coordination protocol.☆24Feb 25, 2026Updated 8 months ago