Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

🐛 fix input text issue #97

Merged
merged 2 commits into from
Aug 19, 2024
Merged

🐛 fix input text issue #97

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
bfff901
🐛 fix input text issue
prashantgupta24 Aug 16, 2024
76f6594
♻️ use request index instead of a map
prashantgupta24 Aug 19, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 5 additions & 1 deletion src/vllm_tgis_adapter/grpc/grpc_server.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -283,6 +283,8 @@ async def Generate(
# # Abort the request if the client disconnects.
# await self.engine.abort(f"{request_id}-{i}")
# return self.create_error_response("Client disconnected")
if res.prompt is None:
res.prompt = request.requests[i].text
responses[i] = res
service_metrics.observe_queue_time(res)

Expand Down Expand Up @@ -322,7 +324,7 @@ async def Generate(
return BatchedGenerationResponse(responses=responses)

@log_rpc_handler_errors
async def GenerateStream(
async def GenerateStream( # noqa: PLR0915
self,
request: SingleGenerationRequest,
context: ServicerContext,
Expand Down Expand Up @@ -378,6 +380,8 @@ async def GenerateStream(
last_engine_response = None
# TODO handle cancellation
async for result in result_generator:
if result.prompt is None:
result.prompt = request.request.text
last_engine_response = result
if first_response is None:
service_metrics.observe_queue_time(result)
Expand Down