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
57f560aa
Unverified
Commit
57f560aa
authored
Aug 05, 2024
by
Aditya Paliwal
Committed by
GitHub
Aug 05, 2024
Browse files
[BugFix] Use args.trust_remote_code (#7121)
parent
003f8ee1
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
3 additions
and
3 deletions
+3
-3
vllm/entrypoints/openai/api_server.py
vllm/entrypoints/openai/api_server.py
+3
-3
No files found.
vllm/entrypoints/openai/api_server.py
View file @
57f560aa
...
...
@@ -60,11 +60,11 @@ logger = init_logger('vllm.entrypoints.openai.api_server')
_running_tasks
:
Set
[
asyncio
.
Task
]
=
set
()
def
model_is_embedding
(
model_name
:
str
)
->
bool
:
def
model_is_embedding
(
model_name
:
str
,
trust_remote_code
:
bool
)
->
bool
:
return
ModelConfig
(
model
=
model_name
,
tokenizer
=
model_name
,
tokenizer_mode
=
"auto"
,
trust_remote_code
=
Fals
e
,
trust_remote_code
=
trust_remote_cod
e
,
seed
=
0
,
dtype
=
"float16"
).
embedding_mode
...
...
@@ -97,7 +97,7 @@ async def build_async_engine_client(args) -> AsyncIterator[AsyncEngineClient]:
# If manually triggered or embedding model, use AsyncLLMEngine in process.
# TODO: support embedding model via RPC.
if
(
model_is_embedding
(
args
.
model
)
if
(
model_is_embedding
(
args
.
model
,
args
.
trust_remote_code
)
or
args
.
disable_frontend_multiprocessing
):
async_engine_client
=
AsyncLLMEngine
.
from_engine_args
(
engine_args
,
usage_context
=
UsageContext
.
OPENAI_API_SERVER
)
...
...
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