# Gpu Cuda

Runs CUDA compute workloads inside a smolvm microVM against a real host NVIDIA GPU...

- Repository: https://github.com/smol-machines/smolvm (6894 stars)
- Category: Media
- License: Apache-2.0
- Last updated: 2026-11-01
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add smol-machines/smolvm --skill gpu-cuda -g -a claude-code -y`
Codex: `npx skills add smol-machines/smolvm --skill gpu-cuda -g -a codex -y`
Cursor: `npx skills add smol-machines/smolvm --skill gpu-cuda -g -a cursor -y`
Gemini CLI: `npx skills add smol-machines/smolvm --skill gpu-cuda -g -a gemini-cli -y`

## Description

Runs CUDA compute workloads inside a smolvm microVM against a real host NVIDIA GPU, using smolvm's --cuda API remoting. Use when a workload in a machine needs a GPU; when nvidia-smi or /dev/nvidia* is missing inside a --cuda guest; when a CUDA program in a machine exits zero but seems not to touch the device; when the shim will not load in an Alpine image; or when checking whether CUDA is available on a given platform, including Windows. Do not use it for Vulkan graphics (--gpu), which is a separate feature, in docs/gpu.md, and do not expect it on a Mac, which has no CUDA driver.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# CUDA inside a machine

Verified on **smolvm v1.22.2** against an **NVIDIA GeForce RTX 4050** (driver 32.0.15.6626,
Windows x86_64), 2026-10-03, and on **v1.14.6** against an **NVIDIA A10** (driver 580.105.08,
Linux x86_64, kernel 6.8.0-1046-nvidia). Done means a program in the VM opens the device, creates a context, and moves
data to and from it.
The Linux runs used the scripts of their date; this version's preflight and cleanup scripts ran
on Linux aarch64 on v1.22.2 on 2026-10-03.

> **The GPU path was last run end to end on Linux x86_64 on v1.14.6**, on an A10: the
> preflight, the probe against two glibc images, all three eval prompts and the cleanup. **Windows
> was re-run on v1.22.2** against an RTX 4050: the probe, the two absences, the shim in a plain
> `alpine` guest, and a vector add over 16777216 elements; see `references/windows.md`. The macOS
> arm64 and Linux aarch64 hosts have no NVIDIA hardware, so what runs there is the no-GPU answer,
> on v1.22.2 on macOS and v1.18.2 on Linux aarch64: the preflight reports `gpu_present=no` without
> starting anything, and `--cuda` reaches a CPU emulation device, which the probe names rather than
> passing. "What was not run" lists every remaining step.

## How this works, and why the checks are shaped this way

The guest gets **no NVIDIA driver and no `/dev/nvidia*`**. A compatibility `libcuda.so.1` is
injected at `/opt/smolvm-cuda` inside the guest and forwards CUDA driver calls over vsock to a host
daemon that owns the device. Nothing is needed on the host beyond a working NVIDIA driver: no extra
packages, no container toolkit, no device plugin.

Because the API is **remoted rather than passed through**, a program can start, link against
`libcuda.so.1` and exit zero without a GPU ever being reached. **Assert a device name and a
transferred result, never an exit code.**

## Procedure

**1. Preflight.**

```bash
scripts/preflight.sh
```

The rest: https://github.com/smol-machines/smolvm/blob/HEAD/docs/gpu-cuda/SKILL.md