
Adds autotuning with cached config selection to CuTile GPU kernels
- Open source
- 4K GitHub stars
- Developer tools

Adds autotuning with cached config selection to CuTile GPU kernels

Guides an agent to write, debug and validate cuTile GPU kernels in Python

Guides an agent through iterative profiling and tuning of cuTile GPU kernels in TileGym

Guides an agent to swap TileGym cuTile kernels into Hugging Face transformers models

Composes and deploys an NVIDIA VSS vision stack with captioning, detection, search

Diagnoses and cuts cold-start compile time in Warp GPU code without changing results

Finds and fixes wrong gradients in differentiable NVIDIA Warp programs using

Checks whether an existing code path is a credible NVIDIA Warp acceleration candidate

Helps agents find and recommend NVIDIA skills from the live catalog before general answers

Guides an agent through GPU DataFrame work with NVIDIA cuDF and dask-cuDF

Runs and ranks cartesian-product parameter sweeps for Proteina-Complexa protein design

Adds and checks Proteina-Complexa design target definitions in YAML registries

Sets up a Docker and GPU environment for KERMT and verifies it runs on the GPU

Guides writing and debugging GPU-accelerated RDKit cheminformatics code with nvMolKit

Finds similar driving clips or generates rain, snow and daylight variations of them

Runs an NVIDIA pipeline that turns seed images into anomaly video clips and datasets

Scaffolds a new custom Kubernetes Airflow DAG for CDF orchestration pipelines from

Runs NVIDIA's video data augmentation Airflow workflow to create and label Cosmos video

Guides an agent to find CUDA memory, shared-memory race and sync bugs with Compute

Guides setup, GPU simulation targets, QPU access and @cudaq.kernel authoring in CUDA-Q

Ports quantum circuits from frameworks like Qiskit into framework-free CUDA-Q kernels

Guides an agent through building a first single-GPU cuDF path in a query engine

Guides an agent through modifying, building, testing and contributing to the cuOpt

Guides installing NVIDIA cuOpt for Python, C, or REST server use via pip, conda or Docker

Traces the Pareto frontier of competing objectives by sweeping repeated cuOpt solves

Guides an agent to model and solve LP, MILP and QP problems with NVIDIA cuOpt

Guides an agent from a plain-text problem to an LP, MILP or QP formulation

Guides an agent through building and solving vehicle routing problems with the cuOpt

Deploy the cuOpt REST server and call its routing and LP/MILP endpoints from Python

Guides agents writing and migrating NVIDIA DALI code to its imperative dynamic-mode API