thustorage / MedusaLinks
Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]
☆30Updated 4 months ago
Alternatives and similar repositories for Medusa
Users that are interested in Medusa are comparing it to the libraries listed below
Sorting:
- ☆51Updated 3 months ago
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆67Updated 10 months ago
- ☆25Updated last year
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆51Updated 2 years ago
- PetPS: Supporting Huge Embedding Models with Tiered Memory☆33Updated last year
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆100Updated 2 years ago
- NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading☆62Updated 3 months ago
- ☆49Updated 2 weeks ago
- ☆36Updated last year
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆62Updated last year
- SHADE: Enable Fundamental Cacheability for Distributed Deep Learning Training☆35Updated 2 years ago
- Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]☆25Updated 10 months ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆53Updated last year
- ☆16Updated last year
- ☆56Updated 4 years ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆205Updated 2 months ago
- [OSDI 2024] Motor: Enabling Multi-Versioning for Distributed Transactions on Disaggregated Memory☆50Updated last year
- Compiler for Dynamic Neural Networks☆46Updated last year
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆43Updated 3 years ago
- A Progam-Behavior-Guided Far Memory System☆35Updated last year
- Stateful LLM Serving☆85Updated 6 months ago
- ☆15Updated 3 years ago
- ☆77Updated 3 years ago
- This is the implementation repository of our SOSP'24 paper: Aceso: Achieving Efficient Fault Tolerance in Memory-Disaggregated Key-Value …☆21Updated 11 months ago
- Deduplication over dis-aggregated memory for Serverless Computing☆14Updated 3 years ago
- Vector search with bounded performance.☆36Updated last year
- ☆32Updated last year
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆129Updated last year
- ☆23Updated last year
- ☆12Updated 5 months ago