Skip to content

[cli] add CLI args for kv cache offloading#1588

Merged
AlpinDale merged 1 commit into
mainfrom
kv-offload-args
Nov 4, 2025
Merged

[cli] add CLI args for kv cache offloading#1588
AlpinDale merged 1 commit into
mainfrom
kv-offload-args

Conversation

@AlpinDale

Copy link
Copy Markdown
Collaborator

Top-level args for enabling KV cache offloading. To test:

aphrodite run Qwen/Qwen3-0.6B --kv-offloading-size 10 --kv-offloading-backend native

Signed-off-by: AlpinDale <alpindale@gmail.com>
@gemini-code-assist

Copy link
Copy Markdown
Contributor

Warning

You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again!

@AlpinDale AlpinDale merged commit 448f0f0 into main Nov 4, 2025
1 check passed
@AlpinDale AlpinDale deleted the kv-offload-args branch November 4, 2025 07:34
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant