This repository was archived by the owner on Mar 5, 2025. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 1
Conversation
This file contains 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: Sophie du Couédic <sop@zurich.ibm.com>
Signed-off-by: Sophie du Couédic <sop@zurich.ibm.com>
…ixed) Signed-off-by: Sophie du Couédic <sop@zurich.ibm.com>
…leanup Signed-off-by: Sophie du Couédic <sop@zurich.ibm.com>
Signed-off-by: Sophie du Couédic <sop@zurich.ibm.com>
Signed-off-by: Sophie du Couédic <sop@zurich.ibm.com>
… validating manually) by setting attribute 'supported_quantization' Signed-off-by: Sophie du Couédic <sop@zurich.ibm.com>
… in vllm Signed-off-by: Sophie du Couédic <sop@zurich.ibm.com>
Signed-off-by: Sophie du Couédic <sop@zurich.ibm.com>
…erence with Spyre Signed-off-by: Sophie du Couédic <sop@zurich.ibm.com>
Signed-off-by: Sophie du Couédic <sop@zurich.ibm.com>
Signed-off-by: Sophie du Couédic <sop@zurich.ibm.com>
Signed-off-by: Yannick Schnider <Yannick.Schnider1@ibm.com>
Signed-off-by: Sophie du Couédic <sop@zurich.ibm.com>
Signed-off-by: Yannick Schnider <yannick.schnider1@ibm.com>
Signed-off-by: Yannick Schnider <yannick.schnider1@ibm.com>
Signed-off-by: Yannick Schnider <yannick.schnider1@ibm.com>
This was referenced Feb 11, 2025
Closed
Signed-off-by: Yannick Schnider <yannick.schnider1@ibm.com>
Signed-off-by: Yannick Schnider <yannick.schnider1@ibm.com>
39518b5
to
900a386
Compare
fbbcc52
to
d9f423c
Compare
0547dd5
to
a5d8fab
Compare
Signed-off-by: Yannick Schnider <yannick.schnider1@ibm.com>
maxdebayser
reviewed
Feb 12, 2025
…re.scheduler Signed-off-by: Yannick Schnider <yannick.schnider1@ibm.com>
c3f76d0
to
9209da2
Compare
sducouedic
previously approved these changes
Feb 13, 2025
We will need to update the |
Need to wait for upstream scheduler plugin PR merged
Signed-off-by: Yannick Schnider <yannick.schnider1@ibm.com>
Signed-off-by: Yannick Schnider <yannick.schnider1@ibm.com>
Signed-off-by: Yannick Schnider <yannick.schnider1@ibm.com>
Signed-off-by: Yannick Schnider <yannick.schnider1@ibm.com>
Signed-off-by: Yannick Schnider <yannick.schnider1@ibm.com>
Signed-off-by: Yannick Schnider <yannick.schnider1@ibm.com>
Signed-off-by: Sophie du Couédic <sop@zurich.ibm.com>
tdoublep
approved these changes
Feb 20, 2025
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
# for free
to subscribe to this conversation on GitHub.
Already have an account?
#.
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.
Adding spyre specific scheduler
This PR integrates the (spyre specific) scheduler class to replace the upstream scheduler.
it goes along with this ->PR<- in the
IBM/vllm
repositoryChanges:
vllm_spyre/core/scheduler.py
: file containing the spyre specificScheduler
classVllmConfig.scheduler_config.worker_cls
invllm_spyre/platform.py
vllm_spyre/envs.py
: adding spyre scheduler related env variables.spyre_warmup_shapes
and code to "load warmup shapes and sort by "speed" shapes" fromvllm/config.py
tovllm-spyre/platform.py