Skip to content

GitLab

Unverified Commit c07526e4 authored by zhyncs's avatar zhyncs Committed by GitHub
Browse files

fix: update bench serving (#694)

parent 7b597475
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 3 deletions
python/sglang/bench_serving.py
View file @ c07526e4
...@@ -70,12 +70,10 @@ async def async_request_trt_llm( ...@@ -70,12 +70,10 @@ async def async_request_trt_llm(
assert api_url.endswith("generate_stream") assert api_url.endswith("generate_stream")
async with aiohttp.ClientSession(timeout=AIOHTTP_TIMEOUT) as session: async with aiohttp.ClientSession(timeout=AIOHTTP_TIMEOUT) as session:
assert not request_func_input.use_beam_search
assert request_func_input.best_of == 1
payload = { payload = {
"accumulate_tokens": True, "accumulate_tokens": True,
"text_input": request_func_input.prompt, "text_input": request_func_input.prompt,
"temperature": 0.0, "temperature": 0.000001,
"top_p": 1.0, "top_p": 1.0,
"max_tokens": request_func_input.output_len, "max_tokens": request_func_input.output_len,
"stream": True, "stream": True,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment