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

[BugFix] Fix tool call finish reason in streaming case #9209

Merged
merged 7 commits into from
Oct 12, 2024
Merged

[BugFix] Fix tool call finish reason in streaming case #9209

Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
3b75e4f
Fix tool call finish reason in streaming case
maxdebayser Oct 9, 2024
70bc2b8
fix formatting
maxdebayser Oct 10, 2024
a4fcd58
Merge branch 'vllm-project:main' into tool_call_finish_reason
maxdebayser Oct 10, 2024
a2e141e
fix editing mistake
maxdebayser Oct 10, 2024
c08c599
make tool call finish reason consistent with OpenAI platform behavior
maxdebayser Oct 10, 2024
07e94c9
Merge branch 'vllm-project:main' into tool_call_finish_reason
maxdebayser Oct 11, 2024
f4992fc
Add comments and improve variable name
maxdebayser Oct 11, 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
Prev Previous commit
Next Next commit
fix formatting 
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
  • Loading branch information
@maxdebayser
maxdebayser committed Oct 10, 2024
commit 70bc2b873080467e7608fa3da715e89feb62efe5
9 changes: 5 additions & 4 deletions vllm/entrypoints/openai/serving_chat.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -539,8 +539,10 @@ async def chat_completion_stream_generator(
# matched by partial json parsing
# only happens if we are NOT using guided decoding
if tool_parser:
tools_called = len(tool_parser.prev_tool_call_arr) > 0
index = len(tool_parser.prev_tool_call_arr) - 1 if tools_called else 0
tools_called = len(
tool_parser.prev_tool_call_arr) > 0
index = len(tool_parser.prev_tool_call_arr
) - 1 if tools_called else 0
tools_called = index > 0
else:
index = 0
Expand Down Expand Up @@ -577,8 +579,7 @@ async def chat_completion_stream_generator(
delta=delta_message,
logprobs=logprobs,
finish_reason=output.finish_reason
if not tools_called
else "tool_calls",
if not tools_called else "tool_calls",
stop_reason=output.stop_reason)
chunk = ChatCompletionStreamResponse(
id=request_id,
Expand Down
Loading