xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-09 12:15:40 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Incorrect another MM data format in vllm bench throughput (#26462)

Browse Source 
Signed-off-by: Huy Do <huydhn@gmail.com>
This commit is contained in:
Huy Do 2025-10-08 22:58:46 -07:00 committed by GitHub
parent bb6d8c21f9
commit 8bd696fa53
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
vllm/benchmarks/throughput.py
View File

@ -59,16 +59,16 @@ def run_vllm(
prompts: list[Union[TextPrompt, TokensPrompt]] = []
sampling_params: list[SamplingParams] = []
for request in requests:
prompts.append(
TokensPrompt(
prompt_token_ids=request.prompt["prompt_token_ids"],
multi_modal_data=request.multi_modal_data,
)
prompt = (
TokensPrompt(prompt_token_ids=request.prompt["prompt_token_ids"])
if "prompt_token_ids" in request.prompt
else TextPrompt(
prompt=request.prompt, multi_modal_data=request.multi_modal_data
)
else TextPrompt(prompt=request.prompt)
)
if request.multi_modal_data:
assert isinstance(request.multi_modal_data, dict)
prompt["multi_modal_data"] = request.multi_modal_data
prompts.append(prompt)
sampling_params.append(
SamplingParams(
n=n,