xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-13 07:46:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Incorrect MM data format in vllm bench throughput (#26395)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung 2025-10-08 13:52:19 +08:00 committed by GitHub
parent 127c8b782a
commit 0d4f48fa10
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

@ -201,16 +201,16 @@ async def run_vllm_async(
sampling_params: list[SamplingParams] = [] sampling_params: list[SamplingParams] = []
lora_requests: list[Optional[LoRARequest]] = [] lora_requests: list[Optional[LoRARequest]] = []
for request in requests: for request in requests:
prompts.append( prompt = (
TokensPrompt( TokensPrompt(prompt_token_ids=request.prompt["prompt_token_ids"])
prompt_token_ids=request.prompt["prompt_token_ids"],
multi_modal_data=request.multi_modal_data,
)
if "prompt_token_ids" in request.prompt if "prompt_token_ids" in request.prompt
else TextPrompt( else TextPrompt(prompt=request.prompt)
prompt=request.prompt, multi_modal_data=request.multi_modal_data
)
) )
if request.multi_modal_data:
assert isinstance(request.multi_modal_data, dict)
prompt["multi_modal_data"] = request.multi_modal_data
sampling_params.append( sampling_params.append(
SamplingParams( SamplingParams(
n=n, n=n,