Simplify multigpu dispatch: all devices on pool threads#13340
Merged
Kosinkadink merged 1 commit intoworksplit-multigpufrom Apr 9, 2026
Merged
Simplify multigpu dispatch: all devices on pool threads#13340Kosinkadink merged 1 commit intoworksplit-multigpufrom
Kosinkadink merged 1 commit intoworksplit-multigpufrom
Conversation
Benchmarked hybrid (main thread + pool) vs all-pool on 2x RTX 4090 with SD1.5 and NetaYume models. No meaningful performance difference (within noise). All-pool is simpler: eliminates the main_device special case, main_batch_tuple deferred execution, and the 3-way branch in the dispatch loop. Amp-Thread-ID: https://ampcode.com/threads/T-019d711f-2c57-744c-acf8-6b98ecd7760e Co-authored-by: Amp <amp@ampcode.com>
Kosinkadink
force-pushed
the
worksplit-multigpu-wip
branch
from
39e9b69 to
a95eabd
Compare
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Benchmarked hybrid (main thread + pool) vs all-pool on 2x RTX 4090 with SD1.5 and NetaYume models. No meaningful performance difference (within noise). All-pool is simpler: eliminates the main_device special case, main_batch_tuple deferred execution, and the 3-way branch in the dispatch loop.
Net result: -15 lines.