[BugFix] Make penalties and bad_words work with async scheduling #26467
+113
−14
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
Signed-off-by: Nick Hill <[email protected]>
njhill
force-pushed
the
async-sched-penalties
branch
from
9803a4b to
24a709f
Compare
Which may store/use the request output_token_ids lists. Signed-off-by: Nick Hill <[email protected]>
Signed-off-by: Nick Hill <[email protected]>
Signed-off-by: Nick Hill <[email protected]>
Signed-off-by: Nick Hill <[email protected]>
njhill
requested review from
ApostaC,
WoosukKwon,
alexm-redhat,
comaniac,
heheda12345,
robertgshaw2-redhat and
ywang96
as code owners
Signed-off-by: Nick Hill <[email protected]>
Signed-off-by: Nick Hill <[email protected]>
|
@WoosukKwon this one is ready. The e2e test also covers combination of these parameters with async sched + preemption. |
WoosukKwon
approved these changes
Oct 10, 2025
Dhruvilbhatt
pushed a commit
to Dhruvilbhatt/vllm
that referenced
this pull request
Oct 14, 2025
…m-project#26467) Signed-off-by: Nick Hill <[email protected]> Signed-off-by: Dhruvil Bhatt <[email protected]>
bbartels
pushed a commit
to bbartels/vllm
that referenced
this pull request
Oct 16, 2025
…m-project#26467) Signed-off-by: Nick Hill <[email protected]> Signed-off-by: bbartels <[email protected]>
lywa1998
pushed a commit
to lywa1998/vllm
that referenced
this pull request
Oct 20, 2025
…m-project#26467) Signed-off-by: Nick Hill <[email protected]>
5 tasks
alhridoy
pushed a commit
to alhridoy/vllm
that referenced
this pull request
Oct 24, 2025
…m-project#26467) Signed-off-by: Nick Hill <[email protected]>
xuebwang-amd
pushed a commit
to xuebwang-amd/vllm
that referenced
this pull request
Oct 24, 2025
…m-project#26467) Signed-off-by: Nick Hill <[email protected]> Signed-off-by: xuebwang-amd <[email protected]>
0xrushi
pushed a commit
to 0xrushi/vllm
that referenced
this pull request
Oct 26, 2025
…m-project#26467) Signed-off-by: Nick Hill <[email protected]> Signed-off-by: 0xrushi <[email protected]>
0xrushi
pushed a commit
to 0xrushi/vllm
that referenced
this pull request
Oct 26, 2025
…m-project#26467) Signed-off-by: Nick Hill <[email protected]> Signed-off-by: 0xrushi <[email protected]>
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.
This is a minimally-invasive fix for compatibility of the current async scheduling implementation with built-in sampling parameters (specifically penalties and bad_words).
We plan to significantly refactor this but would like to first fix existing correctness issues so that async scheduling can be enabled by default.