andrewwhitecdw/zerobrew
A drop-in, 5-20x faster, experimental Homebrew alternative
Andrew White is a Managing Technical Consultant on the AI Factory Team at CDW.
Repositories
andrewwhitecdw/cuda-oxide
cuda-oxide is an experimental Rust-to-CUDA compiler that lets you write (SIMT) GPU kernels in safe(ish), idiomatic Rust. It compiles standard Rust code directly to PTX — no DSLs, no foreign language bindings, just Rust.
andrewwhitecdw/Guardrails
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
andrewwhitecdw/laya
andrewwhitecdw/Lens
andrewwhitecdw/ACCV-Lab
Accelerated Computer Vision Lab (ACCV-Lab) is a systematic collection of packages with the common goal to facilitate end-to-end efficient training in the ADAS domain, each package offering tools & best practices for a specific aspect/task in this domain.
andrewwhitecdw/topograph
A toolkit for discovering cluster network topology.
andrewwhitecdw/cowabungaai
Production-ready Generative AI for local, cloud native, airgap, and edge deployments.
andrewwhitecdw/karta
Translation layer that maps any Kubernetes framework's Custom Resource Definitions (CRDs) into a standardized, generic structure.
andrewwhitecdw/runai-model-streamer
andrewwhitecdw/tensorzero
TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation.
andrewwhitecdw/awdemos
This is my professional portfolio demonstrating my interests in AI, DevOps, and software development.
andrewwhitecdw/infra-controller
NVIDIA Infra Controller - Hardware Lifecycle Management and multitenant networking
andrewwhitecdw/nv-telemetry
Collection of libraries for bare-metal telemetry collection
andrewwhitecdw/libredfish
A Rust Crate for interacting with DTMF Redfish endpoints
andrewwhitecdw/nv-redfish
NVIDIA's Redfish next generation redfish crate
andrewwhitecdw/Automodel
🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support
andrewwhitecdw/cuda-quantum
C++ and Python support for the CUDA Quantum programming model for heterogeneous quantum-classical workflows
andrewwhitecdw/cudf-spark
NVIDIA cuDF for Apache Spark plugin - accelerate Apache Spark with GPUs
andrewwhitecdw/TransformerEngine
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.
andrewwhitecdw/cuda-python
CUDA Python: Performance meets Productivity
andrewwhitecdw/raft
RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.
andrewwhitecdw/gpu-driver-container
The NVIDIA GPU driver container allows the provisioning of the NVIDIA driver through the use of containers.
andrewwhitecdw/fleet-intelligence-agent
NVIDIA Fleet Intelligence Agent - Host agent for GPU telemetry collection and attestation
andrewwhitecdw/attestation-sdk
C++ SDK that provides resources for implementing and validating Trusted Computing Solutions on NVIDIA hardware
andrewwhitecdw/DALI_deps
3rd party dependencies for DALI project
andrewwhitecdw/TileGym
Helpful kernel tutorials, examples and SKILLs for tile-based GPU programming
andrewwhitecdw/nv-config-manager
NVIDIA Switch Infrastructure - Config Manager
andrewwhitecdw/pulumi-rust
Rust SDK and language plugin for the Pulumi Infrastructure as Code Platform (experimental)
andrewwhitecdw/SimFoundry
Modular and Automated Scene Generation for Policy Learning and Evaluation