Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
Menu
Open sidebar
OpenDAS
vllm_cscc
Commits
cdfd6871
Unverified
Commit
cdfd6871
authored
Aug 05, 2025
by
Cyrus Leung
Committed by
GitHub
Aug 04, 2025
Browse files
[Bugfix] Misaligned params in TreeAttentionImpl (#22226)
Signed-off-by:
DarkLight1337
<
tlleungac@connect.ust.hk
>
parent
4b3e4474
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
1 addition
and
5 deletions
+1
-5
vllm/v1/attention/backends/tree_attn.py
vllm/v1/attention/backends/tree_attn.py
+1
-5
No files found.
vllm/v1/attention/backends/tree_attn.py
View file @
cdfd6871
...
...
@@ -4,7 +4,7 @@
import
ast
from
dataclasses
import
dataclass
from
typing
import
TYPE_CHECKING
,
Any
,
Optional
from
typing
import
TYPE_CHECKING
,
Optional
import
torch
...
...
@@ -313,15 +313,11 @@ class TreeAttentionImpl(AttentionImpl):
alibi_slopes
:
Optional
[
list
[
float
]],
sliding_window
:
Optional
[
int
],
kv_cache_dtype
:
str
,
blocksparse_params
:
Optional
[
dict
[
str
,
Any
]]
=
None
,
logits_soft_cap
:
Optional
[
float
]
=
None
,
attn_type
:
AttentionType
=
AttentionType
.
DECODER
,
kv_sharing_target_layer_name
:
Optional
[
str
]
=
None
,
use_irope
:
bool
=
False
,
)
->
None
:
if
blocksparse_params
is
not
None
:
raise
ValueError
(
"TreeAttention does not support block-sparse attention."
)
self
.
num_heads
=
num_heads
self
.
head_size
=
head_size
self
.
scale
=
float
(
scale
)
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment