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
dac914b0
Unverified
Commit
dac914b0
authored
Oct 04, 2024
by
Chen Zhang
Committed by
GitHub
Oct 05, 2024
Browse files
[Bugfix] use blockmanagerv1 for encoder-decoder (#9084)
Co-authored-by:
Roger Wang
<
ywang@roblox.com
>
parent
a95354a3
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
5 additions
and
0 deletions
+5
-0
vllm/engine/arg_utils.py
vllm/engine/arg_utils.py
+5
-0
No files found.
vllm/engine/arg_utils.py
View file @
dac914b0
...
@@ -903,6 +903,11 @@ class EngineArgs:
...
@@ -903,6 +903,11 @@ class EngineArgs:
"--enable-prefix-caching is currently not "
"--enable-prefix-caching is currently not "
"supported for multimodal models and has been disabled."
)
"supported for multimodal models and has been disabled."
)
self
.
enable_prefix_caching
=
False
self
.
enable_prefix_caching
=
False
if
model_config
.
is_encoder_decoder_model
:
logger
.
warning
(
"Block Manager v2 does not support encoder-decoder models"
" currently. Using Block Manager v1 as fallback."
)
self
.
use_v2_block_manager
=
False
cache_config
=
CacheConfig
(
cache_config
=
CacheConfig
(
block_size
=
self
.
block_size
if
self
.
device
!=
"neuron"
else
block_size
=
self
.
block_size
if
self
.
device
!=
"neuron"
else
...
...
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