✨ Use shared CachedRequestData as vllm:main #273
Closed
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: Prashant Gupta <[email protected]>
|
👋 Hi! Thank you for contributing to vLLM support on Spyre. Or this can be done with Now you are good to go 🚀 |
Signed-off-by: Prashant Gupta <[email protected]>
Signed-off-by: Prashant Gupta <[email protected]>
prashantgupta24
changed the title
Signed-off-by: Prashant Gupta <[email protected]>
Signed-off-by: Prashant Gupta <[email protected]>
prashantgupta24
changed the title
Signed-off-by: Prashant Gupta <[email protected]>
Signed-off-by: Prashant Gupta <[email protected]>
prashantgupta24
commented
Jul 2, 2025
Signed-off-by: Prashant Gupta <[email protected]>
Signed-off-by: Prashant Gupta <[email protected]>
Signed-off-by: Prashant Gupta <[email protected]>
|
@prashantgupta24 , I think the other breaking change that you mentioned is the sampling metadata one, right? I've opened a hacky PR to temporarily fix this: #278 |
Yep, thanks! |
Signed-off-by: Prashant Gupta <[email protected]>
Merged
|
closing in favor of #283 |
joerunde
pushed a commit
that referenced
this pull request
Jul 8, 2025
# Description This branch has a fix for: - Caching the token_ids (now the new tokens are cached in `execute_model` instead of `update_states`. This is because of vllm-project/vllm#20291. ) - Changes from the `CachedRequestData` (#273) ## Related Issues Fix for #271 --------- Signed-off-by: Prashant Gupta <[email protected]> Signed-off-by: Max de Bayser <[email protected]> Co-authored-by: Max de Bayser <[email protected]>
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Outdated suggestions cannot be applied.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.
Description
This is more complicated than I thought originally :)
Alright, all tests are passing locally. There seems to be another breaking change in
vllm:mainthat will have to be addressed to make themaintests pass. Thedefaulttests fail because this code is not backward compatible yet 😅Related Issues
fix #271