Skip to content

Temporarily disable prefix caching on Metal #187

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
WindChimeRan merged 1 commit into from
Mar 21, 2026
Merged

Temporarily disable prefix caching on Metal #187

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 9 additions & 0 deletions vllm_metal/platform.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -232,6 +232,15 @@ def check_and_update_config(cls, vllm_config: "VllmConfig") -> None:
scheduler_config.enable_chunked_prefill = False
logger.info("Metal: disabled chunked prefill")

if config.use_paged_attention and getattr(
cache_config, "enable_prefix_caching", False
):
# The unified paged path does not yet safely support vLLM core
# prefix-cache hits for new requests. Disable the feature at the
# platform layer until that path is fully supported.
cache_config.enable_prefix_caching = False
logger.info("Metal: disabled prefix caching")

# Configure cache
if cache_config.block_size is None:
cache_config.block_size = config.block_size
Expand Down
Loading