cuda-13

Here are 3 public repositories matching this topic...

Production-grade SGLang inference on NVIDIA DGX Spark / GB10 (sm_121) — sm_121a-native sgl-kernel, model-agnostic launch recipes, wedge handling.

inference blackwell llm sglang gb10 dgx-spark cuda-13

Pre-built PyTorch wheels and build scripts for NVIDIA DGX Spark (GB10, sm_121, Blackwell, CUDA 13.0, ARM64)

machine-learning deep-learning gpu cuda inference pytorch nvidia arm64 aarch64 fine-tuning blackwell llm gb10 dgx-spark grace-blackwell sm121 cuda-13 pre-built-wheels

Windows NVIDIA-only Triton 3.7.0 build pipeline for RTX 5090 / Blackwell sm_120a, with FP8 tl.dot validation and peak benchmark results.

windows benchmark gpu cuda pytorch nvidia triton windows-build tensor-cores blackwell fp8 triton-lang rtx-5090 triton-windows cuda-13 sm120a fp8-matmul

Add a description, image, and links to the cuda-13 topic page so that developers can more easily learn about it.

To associate your repository with the cuda-13 topic, visit your repo's landing page and select "manage topics."