Closed
Conversation
Signed-off-by: Drew Newberry <anewberry@nvidia.com>
Member
elezar
reviewed
Apr 30, 2026
| GPU support is part of the single-node gateway bootstrap path rather than a separate architecture. | ||
|
|
||
| - `openshell gateway start --gpu` threads GPU device options through `crates/openshell-cli`, `crates/openshell-bootstrap`, and `crates/openshell-bootstrap/src/docker.rs`. | ||
| - `openshell gateway start` auto-detects GPU support and threads GPU device options through `crates/openshell-cli`, `crates/openshell-bootstrap`, and `crates/openshell-bootstrap/src/docker.rs`. Users can force passthrough with `--gpu` or disable auto-detection with `--no-gpu`. |
Member
There was a problem hiding this comment.
Question: Does the gateway still need GPU support? Does the new architecture not delegate this to the driver?
elezar
reviewed
Apr 30, 2026
| ### GPU flags | ||
|
|
||
| The `--gpu` flag on `gateway start` enables GPU passthrough. OpenShell auto-selects CDI when enabled on the daemon and falls back to Docker's NVIDIA GPU request path (`--gpus all`) otherwise. | ||
| `gateway start` enables GPU passthrough automatically when it detects NVIDIA GPU support. The `--gpu` flag forces GPU passthrough even when auto-detection does not find a device. The `--no-gpu` flag disables auto-detection. |
Member
There was a problem hiding this comment.
Question: Does the --no-gpu disable auto detection or disable GPU support?
elezar
reviewed
Apr 30, 2026
Comment on lines
+122
to
+124
| /// Detect NVIDIA GPU support during deploy and enable passthrough when no | ||
| /// explicit GPU device IDs were supplied. | ||
| pub gpu_auto_detect: bool, |
Member
There was a problem hiding this comment.
Question: Is there a reason for a separate value? Does an "auto" element in the gpu list not already do this?
elezar
reviewed
Apr 30, 2026
Comment on lines
+205
to
+210
| let gpu_device_request = docker | ||
| .info() | ||
| .await | ||
| .ok() | ||
| .as_ref() | ||
| .and_then(docker_gpu_device_request_from_info); |
Member
There was a problem hiding this comment.
Question: Is there ONE DockerComputeDriver for all sandboxes, or is there one per sandbox?
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Add GPU support for Docker compute-driver sandboxes and enable gateway GPU passthrough auto-detection on capable Docker hosts.
Related Issue
None
Changes
gateway start, with--gputo force and--no-gputo disable.Testing
cargo fmtcargo test -p openshell-driver-dockercargo test -p openshell-bootstrap auto_detect_gpucargo test -p openshell-cli gateway_startmise run pre-commitfailed on unrelated local port conflict:sandbox_create_keeps_sandbox_with_forwardingfound port8080in use bycom.docke.Checklist