Skip to content

Add additional Informations from the vllm worker #2550

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

Merged
merrymercy merged 4 commits into from
Oct 12, 2023
Merged

Add additional Informations from the vllm worker #2550

Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
339e361
Update vllm_worker.py
SebastianBodza Oct 11, 2023
e6c6531
rollback main
SebastianBodza Oct 12, 2023
f29ddc0
additional informations from vllm added
SebastianBodza Oct 12, 2023
ad958de
run format.sh
SebastianBodza Oct 12, 2023
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
additional informations from vllm added
  • Loading branch information
@SebastianBodza
SebastianBodza committed Oct 12, 2023
commit f29ddc04b728fc7949fc93c174a5780dbdbc2dab
3 changes: 2 additions & 1 deletion fastchat/serve/vllm_worker.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -110,7 +110,8 @@ async def generate_stream(self, params):
text_outputs = [output.text for output in request_output.outputs]
text_outputs = " ".join(text_outputs)
# Note: usage is not supported yet
ret = {"text": text_outputs, "error_code": 0, "usage": {}}
ret = {"text": text_outputs, "error_code": 0, "usage": {}, "cumulative_logprob": [output.cumulative_logprob for output in request_output.outputs],
"prompt_token_len": len(request_output.prompt_token_ids),"output_token_len": [len(output.token_ids) for output in request_output.outputs] , "finish_reason": [output.finish_reason for output in request_output.outputs]}
yield (json.dumps(ret) + "\0").encode()

async def generate(self, params):
Expand Down