Skip to content

Fix VLLMWorker.generate_stream referencing module-level engine instead of self #3853

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

Open
Chessing234 wants to merge 1 commit into
base: main
Choose a base branch
from
+3 −2
Open

Fix VLLMWorker.generate_stream referencing module-level engine instead of self #3853

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
5 changes: 3 additions & 2 deletions fastchat/serve/vllm_worker.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,7 @@ def __init__(
logger.info(
f"Loading the model {self.model_names} on worker {worker_id}, worker type: vLLM worker..."
)
self.llm_engine = llm_engine
self.tokenizer = llm_engine.engine.tokenizer
# This is to support vllm >= 0.2.7 where TokenizerGroup was introduced
# and llm_engine.engine.tokenizer was no longer a raw tokenizer
Expand Down Expand Up @@ -116,7 +117,7 @@ async def generate_stream(self, params):
frequency_penalty=frequency_penalty,
best_of=best_of,
)
results_generator = engine.generate(context, sampling_params, request_id)
results_generator = self.llm_engine.generate(context, sampling_params, request_id)

async for request_output in results_generator:
prompt = request_output.prompt
Expand All @@ -135,7 +136,7 @@ async def generate_stream(self, params):

aborted = False
if request and await request.is_disconnected():
await engine.abort(request_id)
await self.llm_engine.abort(request_id)
request_output.finished = True
aborted = True
for output in request_output.outputs:
Expand Down
Loading