eniac / paellaLinks
Paella: Low-latency Model Serving with Virtualized GPU Scheduling
☆60Updated last year
Alternatives and similar repositories for paella
Users that are interested in paella are comparing it to the libraries listed below
Sorting:
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆62Updated last year
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆99Updated 2 years ago
- ☆50Updated 7 months ago
- An interference-aware scheduler for fine-grained GPU sharing☆143Updated 6 months ago
- ☆80Updated 2 years ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆84Updated 2 years ago
- NCCL Profiling Kit☆141Updated last year
- Artifacts for our ASPLOS'23 paper ElasticFlow☆52Updated last year
- ☆37Updated last month
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆42Updated 3 years ago
- ☆22Updated last year
- Thunder Research Group's Collective Communication Library☆40Updated last month
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆104Updated 3 months ago
- High performance Transformer implementation in C++.☆129Updated 7 months ago
- PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications☆126Updated 3 years ago
- Fine-grained GPU sharing primitives☆143Updated 3 weeks ago
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆53Updated last year
- Synthesizer for optimal collective communication algorithms☆116Updated last year
- A lightweight design for computation-communication overlap.☆155Updated last week
- ☆84Updated 4 months ago
- TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches☆75Updated 2 years ago
- SOTA Learning-augmented Systems☆36Updated 3 years ago
- [ACM EuroSys 2023] Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access☆57Updated 2 weeks ago
- Compiler for Dynamic Neural Networks☆46Updated last year
- An experimental parallel training platform☆54Updated last year
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆198Updated 3 weeks ago
- Microsoft Collective Communication Library☆66Updated 8 months ago
- Artifacts for our NSDI'23 paper TGS☆82Updated last year
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆51Updated 2 years ago
- Model-less Inference Serving☆91Updated last year