Skip to content

bugfix avail_size() overestimation and storage_cache_evicted_req#25

Open
shermanjlim wants to merge 1 commit intocasys-kaist:mainfrom
shermanjlim:bugfix-prefixcache
Open

bugfix avail_size() overestimation and storage_cache_evicted_req#25
shermanjlim wants to merge 1 commit intocasys-kaist:mainfrom
shermanjlim:bugfix-prefixcache

Conversation

@shermanjlim
Copy link
Copy Markdown

Some bugfixes:

  • In avail_size(): RadixCache's avail_size() already returns the result in bytes, so there's no need to multiply by self._bytes_per_token.
  • In storage_cache_evicted_req(): we should be using second_tier_prefix_cache instead of npu_prefix_cache

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