20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

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

Browse Source 
Signed-off-by: Junichi Sato <junichi.sato@sbintuitions.co.jp>
This commit is contained in:
Junichi Sato 2025-01-24 07:02:13 +09:00 committed by GitHub
parent eb5cb5e528
commit 9726ad676d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
benchmarks/backend_request_func.py
View File

@ -245,11 +245,12 @@ async def async_request_openai_completions(
"max_tokens": request_func_input.output_len, "max_tokens": request_func_input.output_len,
"logprobs": request_func_input.logprobs, "logprobs": request_func_input.logprobs,
"stream": True, "stream": True,
"ignore_eos": request_func_input.ignore_eos,
"stream_options": { "stream_options": {
"include_usage": True, "include_usage": True,
}, },
} }
if request_func_input.ignore_eos:
payload["ignore_eos"] = request_func_input.ignore_eos
if request_func_input.extra_body: if request_func_input.extra_body:
payload.update(request_func_input.extra_body) payload.update(request_func_input.extra_body)
headers = { headers = {
@ -297,7 +298,7 @@ async def async_request_openai_completions(
most_recent_timestamp) most_recent_timestamp)
most_recent_timestamp = timestamp most_recent_timestamp = timestamp
generated_text += text generated_text += text or ""
elif usage := data.get("usage"): elif usage := data.get("usage"):
output.output_tokens = usage.get( output.output_tokens = usage.get(
"completion_tokens") "completion_tokens")
@ -348,11 +349,12 @@ async def async_request_openai_chat_completions(
"temperature": 0.0, "temperature": 0.0,
"max_completion_tokens": request_func_input.output_len, "max_completion_tokens": request_func_input.output_len,
"stream": True, "stream": True,
"ignore_eos": request_func_input.ignore_eos,
"stream_options": { "stream_options": {
"include_usage": True, "include_usage": True,
}, },
} }
if request_func_input.ignore_eos:
payload["ignore_eos"] = request_func_input.ignore_eos
if request_func_input.extra_body: if request_func_input.extra_body:
payload.update(request_func_input.extra_body) payload.update(request_func_input.extra_body)
headers = { headers = {
@ -394,7 +396,7 @@ async def async_request_openai_chat_completions(
output.itl.append(timestamp - output.itl.append(timestamp -
most_recent_timestamp) most_recent_timestamp)
generated_text += content generated_text += content or ""
elif usage := data.get("usage"): elif usage := data.get("usage"):
output.output_tokens = usage.get( output.output_tokens = usage.get(
"completion_tokens") "completion_tokens")