Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
OpenDAS
text-generation-inference
Commits
1b914f37
Unverified
Commit
1b914f37
authored
Oct 24, 2024
by
Daniël de Kok
Committed by
GitHub
Oct 24, 2024
Browse files
flashinfer: reminder to remove contiguous call in the future (#2685)
parent
41c26237
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
2 additions
and
0 deletions
+2
-0
server/text_generation_server/layers/attention/cuda.py
server/text_generation_server/layers/attention/cuda.py
+2
-0
No files found.
server/text_generation_server/layers/attention/cuda.py
View file @
1b914f37
...
...
@@ -55,6 +55,7 @@ def paged_attention(
from
text_generation_server.layers.attention.flashinfer
import
decode_state
return
decode_state
.
get
().
forward
(
# TODO: remove `contiguous` call once https://github.com/flashinfer-ai/flashinfer/pull/553 is merged.
query
.
contiguous
(),
paged_kv_cache
=
(
kv_cache
.
key
,
kv_cache
.
value
),
logits_soft_cap
=
softcap
,
...
...
@@ -220,6 +221,7 @@ def attention(
softcap
=
0.0
return
prefill_with_paged_kv_state
.
get
().
forward
(
# TODO: remove `contiguous` call once https://github.com/flashinfer-ai/flashinfer/pull/553 is merged.
query
.
contiguous
(),
causal
=
causal
,
paged_kv_cache
=
(
kv_cache
.
key
,
kv_cache
.
value
),
...
...
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