Menu
View
Theme
Text size
The paper in your inbox every morning
Straight from the source · Glossary

The Tech Gazette

CUDA

Vol. I No. 26 Saturday, October 17, 2026 Closing 12:53 PM UTC · next edition 10:00 AM UTC

Nvidia's platform for programming its GPUs, the software most AI code runs on.

Read more at developer.nvidia.com →

Learn it

  1. NVIDIA DeveloperSep 22, 2026Technical Guides
    Accelerating a ROS 2 Node with an AI Agent and NVIDIA Isaac ROS
  2. Berkeley AI ResearchJul 29, 2026Technical Guides
    From CUDA to MLX: How K-Search Brings Decades of Kernel Expertise to Apple Silicon

In the news

  1. shap (PyPI)Oct 16, 2026Releases
    shap v0.54.1
  2. UnslothOct 15, 2026Releases
    Flash-Attention2, Causal-Conv1D, Mamba_SSM Binaries
  3. OllamaOct 14, 2026Releases
    Ollama 0.40.5: mlx, port the Metal custom kernels to CUDA by @dhiltgen in #18657
  4. arXiv (systems & security) cs.DCOct 14, 2026Research
    Understanding NVIDIA Grace-Blackwell Unified Memory Through Placement-Controlled Microbenchmarks
  5. llama.cppOct 13, 2026Releases
    b11592
  6. llama.cppOct 12, 2026Releases
    b11576
  7. Incidentllama.cppOct 10, 2026Releases
    b11545
  8. llama.cppOct 9, 2026Releases
    b11538
  9. llama.cppOct 9, 2026Releases
    b11534
  10. llama.cppOct 9, 2026Releases
    b11517
  11. ONNX RuntimeOct 9, 2026Releases
    ONNX Runtime CUDA Plugin EP 0.3.0
  12. llama.cppOct 8, 2026Releases
    b11498
  13. Khronos GroupOct 7, 2026News
    NOCL Making Progress as Mesa Gallium/OpenCL atop NVIDIA CUDA
  14. vLLMOct 7, 2026News
    DeepSeek-V4.1-Flash on vLLM: 5x Agentic Throughput Since Day 0
  15. llama.cppOct 6, 2026Releases
    b11457
  16. arXiv cs.LGOct 6, 2026Research
    CNet: A Complex-Valued Deep Learning Framework with Wirtinger Autodifferentiation and FFT--Hadamard Convolution
  17. llama.cppOct 5, 2026Releases
    b11425
  18. llama.cppOct 4, 2026Releases
    b11399
  19. Incidentllama.cppOct 4, 2026Releases
    b11390
  20. llama.cppOct 3, 2026Releases
    b11370