frozenleaves/vllm
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2025-10-20 14:53:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Misc] Enable proxy support in benchmark script (#12356)

Browse Source 
Signed-off-by: Junichi Sato <junichi.sato@sbintuitions.co.jp>
This commit is contained in:
Junichi Sato
2025-01-24 23:58:26 +09:00
committed by GitHub
parent e784c6b998
commit 3bb8e2c9a2
1 changed files with 10 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
benchmarks/backend_request_func.py
View File

@ -51,7 +51,8 @@ async def async_request_tgi(
api_url = request_func_input.api_url
assert api_url.endswith("generate_stream")
async with aiohttp.ClientSession(timeout=AIOHTTP_TIMEOUT) as session:
async with aiohttp.ClientSession(trust_env=True,
timeout=AIOHTTP_TIMEOUT) as session:
params = {
"best_of": request_func_input.best_of,
"max_new_tokens": request_func_input.output_len,
@ -123,7 +124,8 @@ async def async_request_trt_llm(
api_url = request_func_input.api_url
assert api_url.endswith("generate_stream")
async with aiohttp.ClientSession(timeout=AIOHTTP_TIMEOUT) as session:
async with aiohttp.ClientSession(trust_env=True,
timeout=AIOHTTP_TIMEOUT) as session:
assert request_func_input.best_of == 1
payload = {
"accumulate_tokens": True,
@ -187,7 +189,8 @@ async def async_request_deepspeed_mii(
request_func_input: RequestFuncInput,
pbar: Optional[tqdm] = None,
) -> RequestFuncOutput:
async with aiohttp.ClientSession(timeout=AIOHTTP_TIMEOUT) as session:
async with aiohttp.ClientSession(trust_env=True,
timeout=AIOHTTP_TIMEOUT) as session:
assert request_func_input.best_of == 1
payload = {
@ -235,7 +238,8 @@ async def async_request_openai_completions(
("completions", "profile")
), "OpenAI Completions API URL must end with 'completions' or 'profile'."
async with aiohttp.ClientSession(timeout=AIOHTTP_TIMEOUT) as session:
async with aiohttp.ClientSession(trust_env=True,
timeout=AIOHTTP_TIMEOUT) as session:
payload = {
"model": request_func_input.model_name \
if request_func_input.model_name else request_func_input.model,
@ -333,7 +337,8 @@ async def async_request_openai_chat_completions(
"chat/completions"
), "OpenAI Chat Completions API URL must end with 'chat/completions'."
async with aiohttp.ClientSession(timeout=AIOHTTP_TIMEOUT) as session:
async with aiohttp.ClientSession(trust_env=True,
timeout=AIOHTTP_TIMEOUT) as session:
content = [{"type": "text", "text": request_func_input.prompt}]
if request_func_input.multi_modal_content:
content.append(request_func_input.multi_modal_content)