Skip to content
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

[Doc] Remove outdated comment to avoid misunderstanding #9287

Merged
merged 1 commit into from
Oct 11, 2024
Merged

[Doc] Remove outdated comment to avoid misunderstanding #9287

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
7 changes: 3 additions & 4 deletions vllm/core/block_manager_v2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,9 +24,8 @@ class BlockSpaceManagerV2(BlockSpaceManager):
autoregressively-generated tokens, and other advanced features such as
prefix caching, forking/copy-on-write, and sliding-window memory allocation.

The current implementation is partial; in particular prefix caching and
sliding-window are not feature complete. This class implements the design
described in https://github.com/vllm-project/vllm/pull/3492.
This class implements the design described in
https://github.com/vllm-project/vllm/pull/3492.

Lookahead slots
The block manager has the notion of a "lookahead slot". These are slots
Expand Down Expand Up @@ -190,7 +189,7 @@ def allocate(self, seq_group: SequenceGroup) -> None:

assert (request_id
not in self.cross_block_tables), \
"block table already exists"
"block table already exists"

check_no_caching_or_swa_for_blockmgr_encdec(self, seq_group)

Expand Down