Skip to content

[Frontend] Show progress bar for adding requests #17525

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
May 1, 2025
Merged

[Frontend] Show progress bar for adding requests #17525

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 12 additions & 2 deletions vllm/entrypoints/llm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -462,10 +462,12 @@ def generate(
self._validate_and_add_requests(
prompts=parsed_prompts,
params=sampling_params,
use_tqdm=use_tqdm,
lora_request=lora_request,
prompt_adapter_request=prompt_adapter_request,
guided_options=guided_options_request,
priority=priority)
priority=priority,
)

outputs = self._run_engine(use_tqdm=use_tqdm)
return self.engine_class.validate_outputs(outputs, RequestOutput)
Expand Down Expand Up @@ -957,6 +959,7 @@ def encode(
self._validate_and_add_requests(
prompts=parsed_prompts,
params=pooling_params,
use_tqdm=use_tqdm,
lora_request=lora_request,
tokenization_kwargs=tokenization_kwargs,
prompt_adapter_request=prompt_adapter_request,
Expand Down Expand Up @@ -1127,6 +1130,7 @@ def _cross_encoding_score(
self._validate_and_add_requests(
prompts=parsed_prompts,
params=pooling_params,
use_tqdm=use_tqdm,
lora_request=lora_request,
prompt_adapter_request=prompt_adapter_request,
)
Expand Down Expand Up @@ -1332,6 +1336,8 @@ def _validate_and_add_requests(
prompts: Union[PromptType, Sequence[PromptType]],
params: Union[SamplingParams, Sequence[SamplingParams], PoolingParams,
Sequence[PoolingParams]],
*,
use_tqdm: bool,
lora_request: Optional[Union[Sequence[LoRARequest], LoRARequest]],
prompt_adapter_request: Optional[PromptAdapterRequest],
tokenization_kwargs: Optional[dict[str, Any]] = None,
Expand Down Expand Up @@ -1367,7 +1373,11 @@ def _validate_and_add_requests(
sp.output_kind = RequestOutputKind.FINAL_ONLY

# Add requests to the engine.
for i, prompt in enumerate(prompts):
it = prompts
if use_tqdm:
it = tqdm(it, desc="Adding requests")

for i, prompt in enumerate(it):
self._add_request(
prompt,
params[i] if isinstance(params, Sequence) else params,
Expand Down