fix(security): block request-level GPU video backend selection withou… - #47259
Merged
vllm-bot merged 4 commits intoJul 6, 2026
Merged
Conversation
…t VRAM reservation Prevent request-level media_io_kwargs from selecting GPU video backends (e.g. pynvvideocodec) when the engine did not reserve VRAM for them at startup. VideoMediaIO.merge_kwargs() now strips GPU backend overrides from runtime kwargs unless the static config already named that backend, closing a resource exhaustion vector where unreserved CUDA context and decoder-surface allocations could starve the KV cache. Signed-off-by: Juan Pérez de Algaba <jperezde@redhat.com> Signed-off-by: jperezde <jperezde@redhat.com>
jperezdealgaba
requested review from
DarkLight1337,
NickLucche,
tjtanaa and
ywang96
as code owners
July 1, 2026 07:41
![claude[bot]](https://avatars.githubusercontent.com/in/1236702?s=60&v=4){kind=small}
Isotr0py
enabled auto-merge (squash)
July 1, 2026 08:00
jperezdealgaba
commented
Jul 1, 2026
github-actions
Bot
added
the
ready
Add a `requires_gpu` parameter to VIDEO_LOADER_REGISTRY.register() so backends self-declare their GPU requirements at registration time instead of being tracked in a separate frozenset. This keeps the metadata co-located with the registration and makes it trivial for future GPU backends to opt in. Signed-off-by: Juan Pérez de Algaba <jperezde@redhat.com> Signed-off-by: jperezde <jperezde@redhat.com>
auto-merge was automatically disabled
July 2, 2026 08:16
Head branch was pushed to by a user without write access
Signed-off-by: Juan Pérez de Algaba <jperezde@redhat.com> Signed-off-by: jperezde <jperezde@redhat.com>
DarkLight1337
enabled auto-merge (squash)
July 3, 2026 09:03
Contributor
Author
|
The error doens't seem to be caused by my changes |
Member
|
merged! |
NickLucche
pushed a commit
to NickLucche/vllm
that referenced
this pull request
Jul 15, 2026
vllm-project#47259) Signed-off-by: jperezde <jperezde@redhat.com> Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
philippesic
pushed a commit
to philippesic/vllm-semantic-cache
that referenced
this pull request
Jul 19, 2026
vllm-project#47259) Signed-off-by: jperezde <jperezde@redhat.com> Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 participants
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.
Prevent request-level media_io_kwargs from selecting GPU video backends (e.g. pynvvideocodec) when the engine did not reserve VRAM for them at startup. VideoMediaIO.merge_kwargs() now strips GPU backend overrides from runtime kwargs unless the static config already named that backend, closing a resource exhaustion vector where unreserved CUDA context and decoder-surface allocations could starve the KV cache.