James-QiuHaoran / LLM-serving-with-proxy-models
Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction | A tiny BERT model can tell you the verbosity of an LLM (with low latency overhead!)
☆26Updated 8 months ago
Alternatives and similar repositories for LLM-serving-with-proxy-models:
Users that are interested in LLM-serving-with-proxy-models are comparing it to the libraries listed below
- Artifacts for our ASPLOS'23 paper ElasticFlow☆53Updated 9 months ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆48Updated 2 years ago
- ☆18Updated 7 months ago
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆18Updated 2 months ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆145Updated 4 months ago
- ☆64Updated 2 years ago
- SOTA Learning-augmented Systems☆34Updated 2 years ago
- ☆37Updated 3 years ago
- Compiler for Dynamic Neural Networks☆45Updated last year
- ☆16Updated 9 months ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆60Updated 8 months ago
- ☆14Updated 9 months ago
- Stateful LLM Serving☆46Updated 6 months ago
- ☆48Updated 2 years ago
- A Cluster-Wide Model Manager to Accelerate DNN Training via Automated Training Warmup☆34Updated 2 years ago
- Lucid: A Non-Intrusive, Scalable and Interpretable Scheduler for Deep Learning Training Jobs☆52Updated last year
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆10Updated 11 months ago
- Code for "Shockwave: Fair and Efficient Cluster Scheduling for Dynamic Adaptation in Machine Learning" [NSDI '23]☆39Updated 2 years ago
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆17Updated last year
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆53Updated 5 months ago
- ☆16Updated 2 years ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆81Updated last year
- Artifacts for our SIGCOMM'22 paper Muri☆41Updated last year
- ☆23Updated last year
- LLM serving cluster simulator☆92Updated 9 months ago
- Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]☆22Updated 2 months ago
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆40Updated 2 years ago
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆16Updated 2 months ago
- ☆53Updated 4 years ago
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆90Updated 2 years ago