Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]
☆47May 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
- code repo for GCR [FAST'26]☆16Mar 3, 2026Updated 4 months ago
- Foundry materializes CUDA graphs along with its execution context to disk to support fast cold start of serving engines.☆46Jul 8, 2026Updated 2 weeks ago
- The official implementation of OSDI'25 paper BlitzScale☆48Apr 15, 2026Updated 3 months ago
- [NSDI'26] PolyRL is a reinforcement learning framework for LLM that harvest spot instances on the cloud to reduce cost.☆19Mar 30, 2026Updated 3 months ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Fast OS-level support for GPU checkpoint and restore☆285Sep 28, 2025Updated 9 months ago
- Deduplication over dis-aggregated memory for Serverless Computing☆14Mar 21, 2022Updated 4 years ago
- ☆20May 11, 2026Updated 2 months ago
- ☆18Sep 21, 2025Updated 10 months ago
- ☆21May 27, 2025Updated last year
- [FAST'25] ShiftLock: Mitigate One-sided RDMA Lock Contention via Handover.☆20Feb 11, 2025Updated last year
- This is the implementation repository of our SOSP'24 paper: Aceso: Achieving Efficient Fault Tolerance in Memory-Disaggregated Key-Value …☆24Oct 20, 2024Updated last year
- Research prototype of PRISM — a cost-efficient multi-LLM serving system with flexible time- and space-based GPU sharing.☆71Mar 17, 2026Updated 4 months ago
- Examples of usage for Mellanox HW offloads☆17Jan 18, 2022Updated 4 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.
- ☆153Apr 23, 2026Updated 3 months ago
- Code repository for the SOSP'25 paper DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelism.☆21Nov 28, 2025Updated 7 months ago
- Deft: A Scalable Tree Index for Disaggregated Memory☆22Apr 23, 2025Updated last year
- ☆11Aug 9, 2021Updated 4 years ago
- The source code of INFless，a native serverless platform for AI inference.☆46Oct 10, 2022Updated 3 years ago
- [ASPLOS' 26] TetriServe: Efficiently Serving Mixed DiT Workloads☆17Mar 12, 2026Updated 4 months ago
- A caching framework for microservice applications☆24Apr 22, 2024Updated 2 years ago
- ☆23May 2, 2026Updated 2 months ago
- ☆45Oct 15, 2025Updated 9 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆27Oct 1, 2025Updated 9 months ago
- A framework for generating realistic LLM serving workloads☆165May 11, 2026Updated 2 months ago
- NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading☆100Jun 16, 2025Updated last year
- Boosting GPU utilization for LLM serving via dynamic spatial-temporal prefill & decode orchestration☆53Jan 8, 2026Updated 6 months ago
- GPU-CR: GPU Checkpoint & Restore☆25Jun 4, 2026Updated last month
- ☆24Oct 31, 2023Updated 2 years ago
- ☆40Nov 28, 2024Updated last year
- SC'25 UltraAttn: Efficiently Parallelizing Attention through Hierarchical Context-Tiling☆16Aug 14, 2025Updated 11 months ago
- NVIDIA Inference Xfer Library (NIXL)☆1,151Updated this week
- 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.
- Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond☆1,115Updated this week
- Virtual Decoupled Cores: Composable Programming Framework and Runtime for Async GPUs☆20Updated this week
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆280Jun 30, 2026Updated 3 weeks ago
- ☆37Aug 7, 2025Updated 11 months ago
- Next-generation datacenter OS built on kernel bypass to speed up unmodified code while improving platform density and security☆130May 14, 2026Updated 2 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 last year
- [OSDI 2024] Motor: Enabling Multi-Versioning for Distributed Transactions on Disaggregated Memory☆50Mar 3, 2024Updated 2 years ago