fix ray engine crashes on multihost #170
Merged
Conversation
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
richardsliu
approved these changes
Aug 19, 2024
FanhaiLu1
reviewed
Aug 19, 2024
jetstream_pt/ray_engine.py
Outdated
| @@ -113,7 +113,7 @@ def prefill_impl( | |||
| results = ray.get(all_outputs) | |||
| # The prefill function does not return any values; | |||
| # the worker itself manages and maintains the prefill states. | |||
| return results[0] | |||
There was a problem hiding this comment.
Current change will break disaggregation serving. We can still keep this line un-change. Disaggregation do need prefix to be returned in this function.
jetstream_pt/ray_worker.py
Outdated
| @@ -490,7 +487,7 @@ def prefill_ray( | |||
| samples_per_slot=1, | |||
| ) | |||
|
|
|||
| return prefix, result | |||
| return result | |||
There was a problem hiding this comment.
Let's keep the same function signature between interleave and disaggregated serving. Return None, result instead of return result.
sixiang-google
force-pushed
the
sixiang
branch
from
c27cb44 to
ce28303
Compare
sixiang-google
force-pushed
the
sixiang
branch
from
ce28303 to
23fb3f2
Compare
FanhaiLu1
approved these changes
Aug 20, 2024
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Outdated suggestions cannot be applied.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.
Fix #150 without all_gather the kv cache