thustorage / MedusaLinks
Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]
☆23Updated last month
Alternatives and similar repositories for Medusa
Users that are interested in Medusa are comparing it to the libraries listed below
Sorting:
- ☆19Updated 2 weeks ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆52Updated last year
- ☆21Updated last year
- ☆53Updated 4 years ago
- PetPS: Supporting Huge Embedding Models with Tiered Memory☆31Updated last year
- ☆22Updated last year
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆49Updated 7 months ago
- Canvas: Isolated and Adaptive Swapping for Multi-Applications on Remote Memory☆38Updated 2 years ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆50Updated 2 years ago
- ☆34Updated last year
- The source code of INFless,a native serverless platform for AI inference.☆38Updated 2 years ago
- This is the implementation repository of our SOSP'24 paper: Aceso: Achieving Efficient Fault Tolerance in Memory-Disaggregated Key-Value …☆20Updated 8 months ago
- ☆16Updated last year
- ☆50Updated 2 years ago
- SHADE: Enable Fundamental Cacheability for Distributed Deep Learning Training☆35Updated 2 years ago
- Artifacts for our SIGCOMM'22 paper Muri☆42Updated last year
- Compiler for Dynamic Neural Networks☆46Updated last year
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆61Updated last year
- ☆14Updated 3 years ago
- Artifact for "Shockwave: Fair and Efficient Cluster Scheduling for Dynamic Adaptation in Machine Learning" [NSDI '23]☆44Updated 2 years ago
- Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction | A tiny BERT model can tell you the verbosity of an …☆35Updated last year
- This is the implementation repository of our OSDI'23 paper: SMART: A High-Performance Adaptive Radix Tree for Disaggregated Memory.☆61Updated 7 months ago
- Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]☆25Updated 7 months ago
- Scaling Up Memory Disaggregated Applications with SMART☆28Updated last year
- ☆14Updated 11 months ago
- Deft: A Scalable Tree Index for Disaggregated Memory☆17Updated 2 months ago
- GPU-accelerated vector query processing system that supports large vector datasets beyond GPU memory.☆28Updated last year
- ☆12Updated 2 months ago
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆94Updated 2 years ago
- Nu is a new datacenter system that enables developers to build fungible applications that can use datacenter resources wherever they are.☆38Updated last year