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
f9f3b596
Unverified
Commit
f9f3b596
authored
Nov 13, 2025
by
Matthew Bonanni
Committed by
GitHub
Nov 13, 2025
Browse files
[Attention][Bugfix] Fix FA sink support (#28660)
Signed-off-by:
Matthew Bonanni
<
mbonanni@redhat.com
>
parent
119c4927
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
6 additions
and
0 deletions
+6
-0
vllm/v1/attention/backends/flash_attn.py
vllm/v1/attention/backends/flash_attn.py
+6
-0
No files found.
vllm/v1/attention/backends/flash_attn.py
View file @
f9f3b596
...
@@ -130,6 +130,12 @@ class FlashAttentionBackend(AttentionBackend):
...
@@ -130,6 +130,12 @@ class FlashAttentionBackend(AttentionBackend):
return
flash_attn_supports_fp8
()
return
flash_attn_supports_fp8
()
return
kv_cache_dtype
in
[
"auto"
]
return
kv_cache_dtype
in
[
"auto"
]
@
classmethod
def
supports_sink
(
cls
)
->
bool
:
if
not
is_flash_attn_varlen_func_available
():
return
False
return
flash_attn_supports_sinks
()
@
classmethod
@
classmethod
def
supports_compute_capability
(
cls
,
capability
:
DeviceCapability
)
->
bool
:
def
supports_compute_capability
(
cls
,
capability
:
DeviceCapability
)
->
bool
:
return
capability
>=
DeviceCapability
(
8
,
0
)
return
capability
>=
DeviceCapability
(
8
,
0
)
...
...
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