Skip to content

chore: add support for v0.18.0#857

Merged
tjohnson31415 merged 10 commits intotorch-spyre:mainfrom
rafvasq:support-v0.18.0
Mar 25, 2026
Merged

chore: add support for v0.18.0#857
tjohnson31415 merged 10 commits intotorch-spyre:mainfrom
rafvasq:support-v0.18.0

Conversation

@rafvasq
Copy link
Copy Markdown
Collaborator

@rafvasq rafvasq commented Mar 23, 2026

Description

Related Issues

Checklist

  • I have read the contributing guidelines
  • My code follows the project's code style (run bash format.sh)
  • I have added tests for my changes (if applicable)
  • I have updated the documentation (if applicable)
  • My commits include a Signed-off-by: line (DCO compliance)

@github-actions
Copy link
Copy Markdown

👋 Hi! Thank you for contributing to vLLM support on Spyre.
Just a reminder: Make sure that your code passes all the linting checks, otherwise your PR won't be able to be merged. To do so, run ./format.sh.
Now you are good to go 🚀.

We also recommend installing prek and configuring it to check your code before every local commit.

Signed-off-by: Rafael Vasquez <rafvasq21@gmail.com>
Co-authored-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Rafael Vasquez <rafvasq21@gmail.com>
Signed-off-by: Rafael Vasquez <rafvasq21@gmail.com>
rafvasq and others added 3 commits March 23, 2026 13:27
Signed-off-by: Rafael Vasquez <rafvasq21@gmail.com>
Now there is a `user_specified_block_size` variable in CacheConfig.
Probably it was introduced to figure out whether the user changed the
block size or not. In vllm-spyre platform.py we're not technically the user,
but only 64 is valid on Spyre anyway and for some reason, setting the
block_size directly no longer workes because it's overwritten with the
default of 16.

Signed-off-by: Max de Bayser <maxdebayser@gmail.com>
Signed-off-by: Max de Bayser <maxdebayser@gmail.com>
Signed-off-by: Max de Bayser <maxdebayser@gmail.com>
@maxdebayser
Copy link
Copy Markdown
Collaborator

bot:test

@tjohnson31415
Copy link
Copy Markdown
Collaborator

bot:test
MARKERS="spyre and prefix_caching and not quantized"

In 2.10, emtpy_cache() is available but throws an error
because in vllm-spyre we don´t allocate any accelerator.

Since in spyre-next we will do so, I think it's better to
add a check before calling empty_cache() instead of just
replacing the whole thing by a noop

Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
@maxdebayser
Copy link
Copy Markdown
Collaborator

bot:test
MARKERS="spyre and prefix_caching and not quantized"

@maxdebayser
Copy link
Copy Markdown
Collaborator

@rafvasq , @tjohnson31415 , except for the readthedocs check, all other tests are passing. Since this PR doesn't touch the docs, I think it's not a blocker.

@rafvasq
Copy link
Copy Markdown
Collaborator Author

rafvasq commented Mar 25, 2026

Thanks @maxdebayser, yes the unrelated doc failure is fixed in #860.

@rafvasq rafvasq enabled auto-merge (squash) March 25, 2026 14:18
@rafvasq rafvasq disabled auto-merge March 25, 2026 14:18
@rafvasq rafvasq requested a review from tjohnson31415 March 25, 2026 14:18
Comment thread vllm_spyre/platform.py Outdated
@github-actions github-actions Bot added the ready Runs the full CI test suite. Only add to PRs once ready to merge to limit public GHA usage label Mar 25, 2026
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
@maxdebayser
Copy link
Copy Markdown
Collaborator

bot:test
MARKERS="spyre and prefix_caching and not quantized"

1 similar comment
@maxdebayser
Copy link
Copy Markdown
Collaborator

bot:test
MARKERS="spyre and prefix_caching and not quantized"

Comment thread vllm_spyre/platform.py Outdated
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Copy link
Copy Markdown
Collaborator

@tjohnson31415 tjohnson31415 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@tjohnson31415 tjohnson31415 merged commit 2d816a7 into torch-spyre:main Mar 25, 2026
13 of 14 checks passed
@rafvasq rafvasq deleted the support-v0.18.0 branch March 25, 2026 18:56
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ready Runs the full CI test suite. Only add to PRs once ready to merge to limit public GHA usage

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[Feature]: Add support for v0.18.0

3 participants