Support vllm quantization #7297
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
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
ivanvykopal
changed the title
| @@ -27,14 +27,31 @@ def __init__(self, status_code, message): | |||
|
|
|||
|
|
|||
| # check if vllm is installed | |||
| def validate_environment(model: str): | |||
| def validate_environment(model: str, optional_params: Union[dict, None]): | |||
There was a problem hiding this comment.
this should be implemented in the transformation.py -
| @@ -142,7 +159,7 @@ def batch_completions( | |||
| ) | |||
| """ | |||
| try: | |||
| llm, SamplingParams = validate_environment(model=model) | |||
| llm, SamplingParams, optional_params = validate_environment(model=model, optional_params=optional_params) | |||
There was a problem hiding this comment.
can you add a mock test w/ screenshot of this working?
similar to this -
ideally this test would not add the vllm sdk as a dep on the ci/cd pipeline (so maybe use a magicmock object here)
|
Hi @krrishdholakia, thank you for your comments. I have moved the default parameters to Here is the screenshot of the tests. |
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Outdated suggestions cannot be applied.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.
Title
I have implemented a feature for loading quantized models with vellum. The current version does not support quantized models with vllm.
Relevant issues
There is no relevant issue.
Type
🆕 New Feature
Changes
I changed the
validate_environmentinvllm/completion/handler.pyto support the loading of quantized versions of models. It was done by providing several vllm's default parameters and updating them with parameters fromoptional_params.[REQUIRED] Testing - Attach a screenshot of any new tests passing locall
If UI changes, send a screenshot/GIF of working UI fixes