Make the rollout-side offload/onload fan-out async to avoid blocking sync code - #1854
Open
fzyzcjy wants to merge 1 commit into
Open
Make the rollout-side offload/onload fan-out async to avoid blocking sync code#1854fzyzcjy wants to merge 1 commit into
fzyzcjy wants to merge 1 commit into
Conversation
Contributor
|
Caution The consumer version of Gemini Code Assist on GitHub has been sunset. All code review activity has officially ceased. |
fzyzcjy
force-pushed
the
tom/refactor-miles/op3-10
branch
from
August 3, 2026 23:44
1c21446 to
60bb61f
Compare
fzyzcjy
force-pushed
the
tom/refactor-miles/op3-9
branch
2 times, most recently
from
August 4, 2026 00:39
448c30f to
b9946a1
Compare
fzyzcjy
force-pushed
the
tom/refactor-miles/op3-10
branch
2 times, most recently
from
August 4, 2026 06:56
2eb2e1b to
cd4c421
Compare
fzyzcjy
requested review from
Rockdu,
Shi-Dong,
Zhichenzzz,
guapisolo,
jybsuper and
yushengsu-thu
as code owners
August 4, 2026 06:56
fzyzcjy
force-pushed
the
tom/refactor-miles/op3-9
branch
from
August 4, 2026 06:57
b9946a1 to
e10f4c5
Compare
fzyzcjy
force-pushed
the
tom/refactor-miles/op3-10
branch
from
August 10, 2026 06:06
cd4c421 to
de62d6c
Compare
fzyzcjy
force-pushed
the
tom/refactor-miles/op3-9
branch
from
August 10, 2026 06:07
e10f4c5 to
b893f39
Compare
fzyzcjy
force-pushed
the
tom/refactor-miles/op3-10
branch
4 times, most recently
from
August 12, 2026 14:31
6a5194c to
c407f31
Compare
fzyzcjy
force-pushed
the
tom/refactor-miles/op3-9
branch
2 times, most recently
from
August 12, 2026 23:56
b95089c to
a8e3e02
Compare
fzyzcjy
force-pushed
the
tom/refactor-miles/op3-10
branch
2 times, most recently
from
August 13, 2026 06:01
9340358 to
4821dfd
Compare
fzyzcjy
force-pushed
the
tom/refactor-miles/op3-9
branch
from
August 13, 2026 06:01
a8e3e02 to
16da4ad
Compare
…sync code These call sites are about to become direct HTTP calls to the engines' own servers. Turn them into `async def` + `await` now, while they still go through ray, so the switch is a one-line change per call site rather than a control-flow change. ServerGroup.offload / onload / onload_weights_from_disk stop handing their caller a list of pending handles and await their own fan-out; RolloutServer gathers over groups instead of over engines, so the whole server still offloads concurrently.
fzyzcjy
force-pushed
the
tom/refactor-miles/op3-9
branch
from
August 14, 2026 04:45
16da4ad to
c8fa640
Compare
fzyzcjy
force-pushed
the
tom/refactor-miles/op3-10
branch
from
August 14, 2026 04:46
4821dfd to
07cde82
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
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.
Part of #1837