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
change
sglang
Commits
d33955d2
Unverified
Commit
d33955d2
authored
May 01, 2025
by
KCFindstr
Committed by
GitHub
May 01, 2025
Browse files
Properly return error response in vertex_generate HTTP endpoint (#5956)
parent
6fc17596
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
12 additions
and
0 deletions
+12
-0
python/sglang/srt/entrypoints/http_server.py
python/sglang/srt/entrypoints/http_server.py
+2
-0
test/srt/test_vertex_endpoint.py
test/srt/test_vertex_endpoint.py
+10
-0
No files found.
python/sglang/srt/entrypoints/http_server.py
View file @
d33955d2
...
@@ -675,6 +675,8 @@ async def vertex_generate(vertex_req: VertexGenerateReqInput, raw_request: Reque
...
@@ -675,6 +675,8 @@ async def vertex_generate(vertex_req: VertexGenerateReqInput, raw_request: Reque
**
(
vertex_req
.
parameters
or
{}),
**
(
vertex_req
.
parameters
or
{}),
)
)
ret
=
await
generate_request
(
req
,
raw_request
)
ret
=
await
generate_request
(
req
,
raw_request
)
if
isinstance
(
ret
,
Response
):
return
ret
return
ORJSONResponse
({
"predictions"
:
ret
})
return
ORJSONResponse
({
"predictions"
:
ret
})
...
...
test/srt/test_vertex_endpoint.py
View file @
d33955d2
...
@@ -3,6 +3,7 @@ python3 -m unittest test_vertex_endpoint.TestVertexEndpoint.test_vertex_generate
...
@@ -3,6 +3,7 @@ python3 -m unittest test_vertex_endpoint.TestVertexEndpoint.test_vertex_generate
"""
"""
import
unittest
import
unittest
from
http
import
HTTPStatus
import
requests
import
requests
...
@@ -49,6 +50,15 @@ class TestVertexEndpoint(CustomTestCase):
...
@@ -49,6 +50,15 @@ class TestVertexEndpoint(CustomTestCase):
for
parameters
in
[
None
,
{
"sampling_params"
:
{
"max_new_tokens"
:
4
}}]:
for
parameters
in
[
None
,
{
"sampling_params"
:
{
"max_new_tokens"
:
4
}}]:
self
.
run_generate
(
parameters
)
self
.
run_generate
(
parameters
)
def
test_vertex_generate_fail
(
self
):
data
=
{
"instances"
:
[
{
"prompt"
:
"The capital of France is"
},
],
}
response
=
requests
.
post
(
self
.
base_url
+
"/vertex_generate"
,
json
=
data
)
assert
response
.
status_code
==
HTTPStatus
.
BAD_REQUEST
if
__name__
==
"__main__"
:
if
__name__
==
"__main__"
:
unittest
.
main
()
unittest
.
main
()
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