Skip to content

[Misc] Fix OpenAI API Compatibility Issues in Benchmark Script #12357

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
merged 1 commit into from
Jan 23, 2025
Merged

[Misc] Fix OpenAI API Compatibility Issues in Benchmark Script #12357

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
10 changes: 6 additions & 4 deletions benchmarks/backend_request_func.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -245,11 +245,12 @@ async def async_request_openai_completions(
"max_tokens": request_func_input.output_len,
"logprobs": request_func_input.logprobs,
"stream": True,
"ignore_eos": request_func_input.ignore_eos,
"stream_options": {
"include_usage": True,
},
}
if request_func_input.ignore_eos:
payload["ignore_eos"] = request_func_input.ignore_eos
if request_func_input.extra_body:
payload.update(request_func_input.extra_body)
headers = {
Expand Down Expand Up @@ -297,7 +298,7 @@ async def async_request_openai_completions(
most_recent_timestamp)

most_recent_timestamp = timestamp
generated_text += text
generated_text += text or ""
elif usage := data.get("usage"):
output.output_tokens = usage.get(
"completion_tokens")
Expand Down Expand Up @@ -348,11 +349,12 @@ async def async_request_openai_chat_completions(
"temperature": 0.0,
"max_completion_tokens": request_func_input.output_len,
"stream": True,
"ignore_eos": request_func_input.ignore_eos,
"stream_options": {
"include_usage": True,
},
}
if request_func_input.ignore_eos:
payload["ignore_eos"] = request_func_input.ignore_eos
if request_func_input.extra_body:
payload.update(request_func_input.extra_body)
headers = {
Expand Down Expand Up @@ -394,7 +396,7 @@ async def async_request_openai_chat_completions(
output.itl.append(timestamp -
most_recent_timestamp)

generated_text += content
generated_text += content or ""
elif usage := data.get("usage"):
output.output_tokens = usage.get(
"completion_tokens")
Expand Down
Loading