Repository navigation
fix(m3): score a single pair on multiple devices - #1616
Open
michaelkillgta wants to merge 1 commit into
Open
michaelkillgta wants to merge 1 commit into
michaelkillgta wants to merge 1 commit into
Conversation
This branch has not been deployed
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #1615
BGEM3FlagModel.compute_scorepassed a single(query, passage)tuple straight to the multi-process pool when more than one device is set. The pool iterated over the tuple, the workers received bare strings and failed withIndexError, and the parent then waited on the output queue forever.The multi-device path now wraps a single pair before dispatch and unwraps the result afterwards, so it returns one float per mode, the same as on a single device.
Tests: added
tests/test_m3_compute_score_multi_device.py, which stubs the pool (no model download). The single-pair test fails on master and passes with this change, and the pair-list test passes on both. I also reproduced the original hang end to end withBAAI/bge-m3ondevices=["cpu", "cpu"].