James-QiuHaoran / LLM-serving-with-proxy-models
Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction | A tiny model can tell you the verbosity of an LLM (with low latency!)
☆22Updated 5 months ago
Related projects ⓘ
Alternatives and complementary repositories for LLM-serving-with-proxy-models
- Artifacts for our ASPLOS'23 paper ElasticFlow☆52Updated 6 months ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆47Updated last year
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆57Updated 5 months ago
- ☆48Updated last year
- ☆51Updated 3 years ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆135Updated last month
- Stateful LLM Serving☆38Updated 3 months ago
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆8Updated 8 months ago
- SOTA Learning-augmented Systems☆33Updated 2 years ago
- ☆14Updated 5 months ago
- ☆46Updated 5 months ago
- Compiler for Dynamic Neural Networks☆43Updated last year
- ☆56Updated 2 years ago
- ☆24Updated last year
- ☆15Updated 4 months ago
- ☆37Updated 3 years ago
- ☆23Updated 2 years ago
- ☆56Updated last week
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆79Updated last year
- ☆16Updated last year
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆102Updated 9 months ago
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆54Updated 3 months ago
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆85Updated last year
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆14Updated 11 months ago
- Helios Traces from SenseTime☆49Updated 2 years ago
- LLM serving cluster simulator☆81Updated 6 months ago
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆57Updated 6 months ago
- ☆41Updated last year
- Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access (ACM EuroSys '23)☆54Updated 7 months ago
- ☆23Updated last year