eniac / paellaLinks
Paella: Low-latency Model Serving with Virtualized GPU Scheduling
☆62Updated last year
Alternatives and similar repositories for paella
Users that are interested in paella are comparing it to the libraries listed below
Sorting:
- 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
- ☆50Updated 8 months ago
- An interference-aware scheduler for fine-grained GPU sharing☆145Updated 7 months ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆52Updated last year
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆84Updated 2 years ago
- ☆81Updated 2 years ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆62Updated last year
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆43Updated 3 years ago
- ☆37Updated 2 months ago
- ☆22Updated last year
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆53Updated last year
- High performance Transformer implementation in C++.☆132Updated 7 months ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆203Updated last month
- PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications☆126Updated 3 years ago
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆64Updated 9 months ago
- Compiler for Dynamic Neural Networks☆46Updated last year
- A lightweight design for computation-communication overlap.☆161Updated this week
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆51Updated 2 years ago
- TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches☆74Updated 2 years ago
- NCCL Profiling Kit☆143Updated last year
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆13Updated last year
- An experimental parallel training platform☆54Updated last year
- Microsoft Collective Communication Library☆66Updated 9 months ago
- Artifacts for our NSDI'23 paper TGS☆84Updated last year
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆108Updated 3 months ago
- Here are my personal paper reading notes (including cloud computing, resource management, systems, machine learning, deep learning, and o…☆120Updated 3 weeks ago
- Thunder Research Group's Collective Communication Library☆41Updated 2 months ago
- ☆42Updated last month
- PerFlow-AI is a programmable performance analysis, modeling, prediction tool for AI system.☆23Updated this week
- LLM serving cluster simulator☆109Updated last year