NVIDIA · GPU Data Acquisition
NVIDIA DAQIRI
DAQIRI is a software-defined data acquisition library from NVIDIA, part of the Holoscan platform, that receives high-bandwidth instrument data directly into GPU memory for processing during acquisition. The latest release adds hardware packet reordering on ConnectX-7 or newer NICs, an ibverbs engine that nearly doubles per-core throughput at small packet sizes, and a direct polling mode with 2-4 µs application send-to-receive latency. The post uses a Berkeley Lab electron microscopy camera producing over 500 Gbps as the case study.
Open the source ↗Similar Developer Tools releases
- NVIDIA DGX Spark HPC Developer Kit
NVIDIA · Desktop AI Cluster · Week 48, 2026
- Altar
Aikido Security · Altar Sovereign Security · Week 40, 2026
- Uncensored Local AI Multiplatform v2.0.0
techjarves · Offline Local LLM App · Week 37, 2026
- LTX-2 Trainer
Lightricks · AI Infrastructure · Week 25, 2026
- Odysseus
pewdiepie-archdaemon · Inference Engine · Week 23, 2026
- Hunyuan3D 2.0/2.1 Windows Portable
YanWenKun · Edge Deployment · Week 19, 2026
More from NVIDIA
- NVIDIA Cosmos Data Factory
NVIDIA · Physical AI data · Week 48, 2026
- Nemotron for Science
NVIDIA · Science Agent Toolkit · Week 48, 2026
- Nemotron RL Litmus-Bench V2.0
NVIDIA · Science Post-Training Dataset · Week 48, 2026
- NVIDIA Vera Rubin NVL72 in MLPerf Training v6.1
NVIDIA · Training Benchmark Results · Week 48, 2026
- NVIDIA Rubin HPC
NVIDIA · HPC GPU for Agents · Week 48, 2026
- NVIDIA CUDA-X libraries (cuPhoton, cuPotential, cuSpa, Daviator, rapids-singlecell)
NVIDIA · GPU Science Libraries · Week 48, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.