Sop plugin refactoring #75
Open
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: Thomas Parnell <tpa@zurich.ibm.com>
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
this PR improves code readability by - [commit 1](0c9bec0): removing the batch size argument in the load_model function [here](https://github.com/IBM/vllm/blob/124f3a961d1a9ce2628c01fe56dfcc589a49c8dd/vllm/worker/spyre_worker.py#L135) since unused in `SpyreModelRunner` ([here](https://github.com/IBM/vllm/blob/124f3a961d1a9ce2628c01fe56dfcc589a49c8dd/vllm/worker/spyre_model_runner.py#L104)) as well as in `SpyreEmbeddingModelRunner` ([here](https://github.com/IBM/vllm/blob/124f3a961d1a9ce2628c01fe56dfcc589a49c8dd/vllm/worker/spyre_embedding_model_runner.py#L52)). - -- _[commit 2](beadbd5): function renaming to better distinguish between the imported function `init_distributed_environment` from `vllm.distributed` and our own function `self.init_distributed_environment`._ -- (**reverted since this seems to be a convention introduced in other worker classes**) --------- Signed-off-by: Yannick Schnider <Yannick.Schnider1@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: Sophie du Couédic <sop@zurich.ibm.com>
…ed to pluging and tested Signed-off-by: Sophie du Couédic <sop@zurich.ibm.com>
… by setting attribute 'supported_quantization' in the plugin 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: Sophie du Couédic <sop@zurich.ibm.com>
Signed-off-by: Sophie du Couédic <sop@zurich.ibm.com>
…e_type' in Platform Signed-off-by: Sophie du Couédic <sop@zurich.ibm.com>
Signed-off-by: Sophie du Couédic <sop@zurich.ibm.com>
|
👋 Hi! Thank you for contributing to the vLLM project. Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging. To run CI, PR reviewers can do one of these:
🚀 |
sducouedic
added
github_actions
Signed-off-by: Sophie du Couédic <sop@zurich.ibm.com>
Signed-off-by: Sophie du Couédic <sop@zurich.ibm.com>
This PR moves the (spyre specific) scheduler class into the plugin repo `vllm-spyre`. it goes along with this ->[PR](https://github.com/IBM/vllm-spyre/pull/4)<- in the `vllm-spyre` repository Changes: - `vllm/config.py`: introducing new variable `scheduler_cls` for class `SchedulerConfig` (can be a path (str) or a class directly) and removing spyre specific code to 'load warmup shapes and sort by "speed"' (moved to `vllm-spyre`) - `vllm/engine/llm_engine.py`: importing `Scheduler` based on `vllm_config.scheduler_config.scheduler_cls` - `vllm/core/scheduler.py`: removing all spyre specific code from the scheduler logic - `vllm/envs.py`: removing all spyre related env variables (moved to `vllm-spyre`) - remove the variable: `SchedulerConfig.spyre_warmup_shapes` in `vllm/vllm.config.py` --------- Signed-off-by: Yannick Schnider <yannick.schnider1@ibm.com>
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.
This PR goes along with this other PR (see detailed description of the refactoring there), to make vllm supporting spyre a plugin. Only remaining spyre-related code is for the scheduler.
Edit 07.02.2025: Change target branch from
upstream-2025-01-17tomain.