alibaba / llm-scheduling-artifactLinks
Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“
☆62Updated last year
Alternatives and similar repositories for llm-scheduling-artifact
Users that are interested in llm-scheduling-artifact are comparing it to the libraries listed below
Sorting:
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆84Updated 2 years ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆203Updated last month
- Stateful LLM Serving☆81Updated 6 months ago
- LLM serving cluster simulator☆109Updated last year
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆128Updated last year
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆53Updated last year
- ☆84Updated 5 months ago
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆64Updated 9 months ago
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆62Updated 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
- Artifacts for our ASPLOS'23 paper ElasticFlow☆52Updated last year
- ☆120Updated 10 months ago
- ☆24Updated last year
- Compiler for Dynamic Neural Networks☆46Updated last year
- High performance Transformer implementation in C++.☆132Updated 7 months ago
- ☆76Updated 3 years ago
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆108Updated 3 months ago
- This repository is established to store personal notes and annotated papers during daily research.☆148Updated last month
- An interference-aware scheduler for fine-grained GPU sharing☆145Updated 7 months ago
- A lightweight design for computation-communication overlap.☆161Updated last week
- ☆47Updated 3 months ago
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆43Updated 3 years ago
- ☆20Updated last year
- ☆81Updated 2 years ago
- ☆69Updated last year
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆51Updated 2 years ago
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆13Updated last year
- ☆23Updated last year
- PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications☆126Updated 3 years ago
- A resilient distributed training framework☆94Updated last year