🐛 Fix tiered-prefix-cache CrashLoopBackOff: num_cpu_blocks → cpu_bytes_to_use#768
Merged
clubanderson merged 1 commit intomainfrom Feb 14, 2026
Merged
🐛 Fix tiered-prefix-cache CrashLoopBackOff: num_cpu_blocks → cpu_bytes_to_use#768clubanderson merged 1 commit intomainfrom
clubanderson merged 1 commit intomainfrom
Conversation
…s_to_use vLLM v0.14.1 (PR #24498, merged Jan 12 2026) replaced the `num_cpu_blocks` config key with `cpu_bytes_to_use` in the OffloadingConnector's CPUOffloadingSpec. This causes model server pods to crash immediately with: Exception: cpu_bytes_to_use must be specified in kv_connector_extra_config Update all references: - Guide manifest: 41000 blocks (~100GB) → 107374182400 bytes (100GB) - Nightly slim patch: 4000 blocks (~10GB) → 10737418240 bytes (10GB) - README benchmark section: updated parameter name Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> Signed-off-by: Andrew Anderson <andy@clubanderson.com>
Contributor
Author
|
@Gregory-Pereira ptal! |
Contributor
Author
|
this was reverted - will open new pr |
24 tasks
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
num_cpu_blockswithcpu_bytes_to_usein theOffloadingConnector'sCPUOffloadingSpecnum_cpu_blocksparameter, causing:Exception: cpu_bytes_to_use must be specified in kv_connector_extra_configChanges
offloading-connector/kustomization.yaml):num_cpu_blocks: 41000→cpu_bytes_to_use: 107374182400(100GB)nightly-e2e-tiered-prefix-cache.yaml):num_cpu_blocks: 4000→cpu_bytes_to_use: 10737418240(10GB)README.md): Updated parameter referenceTest plan
kubectl apply -k guides/tiered-prefix-cache/cpu/manifests/vllm/offloading-connectordeploys successfully