squall/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Doc] Remove outdated comment to avoid misunderstanding (#9287)

Browse Source
This commit is contained in:
homeffjy 2024-10-12 02:02:03 +08:00 committed by GitHub
parent 6cf1167c1a
commit 1a1823871d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
vllm/core/block_manager_v2.py
View File

@ -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
@ -190,7 +189,7 @@ class BlockSpaceManagerV2(BlockSpaceManager):
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)