NVIDIA-DOCA / gpunetioLinks
Open source version of DOCA GPUNetIO and DOCA Verbs libraries (limited features) to enable GDAKI technology on RDMA (IB and RoCE)
☆19Updated 2 months ago
Alternatives and similar repositories for gpunetio
Users that are interested in gpunetio are comparing it to the libraries listed below
Sorting:
- TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches☆77Updated 2 years ago
- An interference-aware scheduler for fine-grained GPU sharing☆153Updated last week
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆103Updated 2 years ago
- ☆226Updated 2 months ago
- ☆21Updated 9 months ago
- ☆61Updated last month
- ☆23Updated 2 years ago
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆73Updated last month
- Here are my personal paper reading notes (including cloud computing, resource management, systems, machine learning, deep learning, and o…☆137Updated 3 weeks ago
- This repository is established to store personal notes and annotated papers during daily research.☆165Updated this week
- Injecting Adrenaline into LLM Serving: Boosting Resource Utilization and Throughput via Attention Disaggregation☆39Updated 3 weeks ago
- Synthesizer for optimal collective communication algorithms☆121Updated last year
- ☆53Updated 11 months ago
- NCCL Profiling Kit☆149Updated last year
- Artifacts for our NSDI'23 paper TGS☆90Updated last year
- ☆23Updated last year
- ☆42Updated last year
- Artifact from "Hardware Compute Partitioning on NVIDIA GPUs". THIS IS A FORK OF BAKITAS REPO. I AM NOT ONE OF THE AUTHORS OF THE PAPER.☆42Updated last week
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆65Updated last year
- ☆79Updated 3 years ago
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆40Updated 6 months ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆220Updated 4 months ago
- ☆10Updated 11 months ago
- ☆27Updated last year
- Artifacts for our ASPLOS'23 paper ElasticFlow☆55Updated last year
- ☆31Updated last year
- ☆40Updated 2 years ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆54Updated 2 years ago
- Repository for MLCommons Chakra schema and tools☆142Updated last month
- ☆38Updated 5 months ago