James-QiuHaoran / LLM-serving-with-proxy-modelsLinks
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!)
☆49Updated last year
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
Sorting:
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆226Updated 5 months ago
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆74Updated 2 months ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆55Updated last year
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆133Updated last year
- [ASPLOS'25] Towards End-to-End Optimization of LLM-based Applications with Ayo☆56Updated 4 months ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆92Updated 2 years ago
- This repository is established to store personal notes and annotated papers during daily research.☆169Updated this week
- ☆28Updated last year
- LLM serving cluster simulator☆127Updated last year
- ☆79Updated 3 years ago
- ☆42Updated last year
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆64Updated last year
- ☆51Updated 3 years ago
- ☆20Updated last year
- A resilient distributed training framework☆96Updated last year
- ☆44Updated last year
- Stateful LLM Serving☆90Updated 9 months ago
- ☆69Updated last month
- A framework for generating realistic LLM serving workloads☆93Updated 2 months ago
- An interference-aware scheduler for fine-grained GPU sharing☆154Updated 3 weeks ago
- ☆156Updated 5 months ago
- ☆79Updated 2 months ago
- ☆24Updated last year
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆40Updated 7 months ago
- Compiler for Dynamic Neural Networks☆46Updated 2 years ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆54Updated 3 years ago
- Here are my personal paper reading notes (including cloud computing, resource management, systems, machine learning, deep learning, and o…☆141Updated last month
- The source code of INFless，a native serverless platform for AI inference.☆44Updated 3 years ago
- Lucid: A Non-Intrusive, Scalable and Interpretable Scheduler for Deep Learning Training Jobs☆58Updated 2 years ago
- Artifacts for our NSDI'23 paper TGS☆93Updated last year