Add LLM-inference (vLLM KV-cache + queue) external scaler - #34
Open
kornsour wants to merge 1 commit into
Open
Conversation
kornsour
force-pushed
the
add-llm-inference-scaler
branch
from
June 24, 2026 19:39
fd41087 to
7076c4e
Compare
…aler Signed-off-by: kornsour <ajkaiserauer@gmail.com>
kornsour
force-pushed
the
add-llm-inference-scaler
branch
from
June 24, 2026 19:50
7076c4e to
1eac68b
Compare
kornsour
marked this pull request as ready for review
June 24, 2026 19:56
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds a community external scaler to the list: an inference-aware KEDA external scaler for LLM serving (vLLM).
It scales on a composite signal —
max(queueDepth / threshold, kvCacheUtil / threshold)— combining request-queue depth and KV-cache utilization in a single trigger, which the built-in single-query Prometheus scaler can't express. Written in Go (implements the external-scaler gRPC contract); ships a Dockerfile, unit tests, an exampleScaledObject, and CI.Source: https://github.com/kornsour/keda-inference-scaler