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

LLM: Fix /generate_stream api in Pipeline Parallel FastAPI #11569

Merged
merged 1 commit into from
Jul 12, 2024
Merged

LLM: Fix /generate_stream api in Pipeline Parallel FastAPI #11569

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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 python/llm/example/GPU/Pipeline-Parallel-FastAPI/pipeline_serving.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -192,7 +192,6 @@ async def generate(prompt_request: PromptRequest):
return request_id, "".join(output_str)


@app.post("/generate_stream/")
async def generate_stream(prompt_request: PromptRequest):
request_id = str(uuid.uuid4()) + "stream"
await local_model.waiting_requests.put((request_id, prompt_request))
Expand All @@ -211,6 +210,11 @@ async def generate_stream(prompt_request: PromptRequest):
content=cur_generator, media_type="text/event-stream"
)

@app.post("/generate_stream/")
async def generate_stream_api(prompt_request: PromptRequest):
request_id, result = await generate_stream(prompt_request)
return result


DEFAULT_SYSTEM_PROMPT = """\
"""
Expand Down
Loading