dywsjtu / apparateLinks
Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]
☆25Updated 9 months ago
Alternatives and similar repositories for apparate
Users that are interested in apparate are comparing it to the libraries listed below
Sorting:
- A Cluster-Wide Model Manager to Accelerate DNN Training via Automated Training Warmup☆35Updated 2 years ago
- ☆25Updated last year
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆29Updated 3 months ago
- SOTA Learning-augmented Systems☆36Updated 3 years ago
- ☆16Updated last year
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆128Updated last year
- Stateful LLM Serving☆81Updated 5 months ago
- Vector search with bounded performance.☆36Updated last year
- Artifact for "Shockwave: Fair and Efficient Cluster Scheduling for Dynamic Adaptation in Machine Learning" [NSDI '23]☆45Updated 2 years ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆62Updated last year
- ☆15Updated 3 years ago
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆60Updated 8 months ago
- Efficient Compute-Communication Overlap for Distributed LLM Inference☆30Updated last month
- A resilient distributed training framework☆94Updated last year
- Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction | A tiny BERT model can tell you the verbosity of an …☆40Updated last year
- ☆55Updated 4 years ago
- Deferred Continuous Batching in Resource-Efficient Large Language Model Serving (EuroMLSys 2024)☆16Updated last year
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆84Updated 2 years ago
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆53Updated last year
- ☆68Updated last year
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆51Updated 2 years ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆52Updated last year
- A framework for generating realistic LLM serving workloads☆53Updated 2 months ago
- ☆12Updated 4 months ago
- Official resporitory for "IPDPS' 24 QSync: Quantization-Minimized Synchronous Distributed Training Across Hybrid Devices".☆20Updated last year
- Artifacts for our SIGCOMM'22 paper Muri☆42Updated last year
- ☆120Updated 10 months ago
- ☆42Updated 2 months ago
- ☆24Updated last year
- ☆33Updated last year