AMD Support#35
Merged
Merged
Conversation
These are deprecated on HIP. Apparently you're supposed to use device and stream APIs
Instead of building with the nvidia SDK, use the runtime function getting and a ducktype header to eliminate the dependency.
Amp-Thread-ID: https://ampcode.com/threads/T-019d9be9-f878-771b-9d48-6c18e74ef6d3 Co-authored-by: Amp <amp@ampcode.com>
The hip way was correct and cuda needed to catch up. Factor it out to get the os stuff split down OS and dedup the core in dispatch.
|
I thought I had some commits here as well, but GitHub says "Think again" XD I must have an alter ego that shows up in https://github.com/Comfy-Org/comfy-aimdo/pull/35/commits. |
Contributor
|
I tried this and things seem to be working fine, so at least immediately I'm not seeing this causing any regressions and model switching behaviour is improved, compared to without aimdo. |
This was referenced Apr 21, 2026
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
5 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Contribution Agreement
Refactor Nvidia to link everything at runtime via libdl (and windows equivalents, and then implement AMD support via HIP the same way.
PR #2 is merged in with a conflict resolution and the basic rework for the runtime linkage.