xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-12 16:06:07 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Frontend] Show progress bar for adding requests (#17525)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung 2025-05-01 20:15:32 +08:00 committed by GitHub
parent 86a1f67a3b
commit 1903c0b8a3
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 12 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
vllm/entrypoints/llm.py
View File

@ -462,10 +462,12 @@ class LLM:
self._validate_and_add_requests( self._validate_and_add_requests(
prompts=parsed_prompts, prompts=parsed_prompts,
params=sampling_params, params=sampling_params,
use_tqdm=use_tqdm,
lora_request=lora_request, lora_request=lora_request,
prompt_adapter_request=prompt_adapter_request, prompt_adapter_request=prompt_adapter_request,
guided_options=guided_options_request, guided_options=guided_options_request,
priority=priority) priority=priority,
)
outputs = self._run_engine(use_tqdm=use_tqdm) outputs = self._run_engine(use_tqdm=use_tqdm)
return self.engine_class.validate_outputs(outputs, RequestOutput) return self.engine_class.validate_outputs(outputs, RequestOutput)
@ -957,6 +959,7 @@ class LLM:
self._validate_and_add_requests( self._validate_and_add_requests(
prompts=parsed_prompts, prompts=parsed_prompts,
params=pooling_params, params=pooling_params,
use_tqdm=use_tqdm,
lora_request=lora_request, lora_request=lora_request,
tokenization_kwargs=tokenization_kwargs, tokenization_kwargs=tokenization_kwargs,
prompt_adapter_request=prompt_adapter_request, prompt_adapter_request=prompt_adapter_request,
@ -1127,6 +1130,7 @@ class LLM:
self._validate_and_add_requests( self._validate_and_add_requests(
prompts=parsed_prompts, prompts=parsed_prompts,
params=pooling_params, params=pooling_params,
use_tqdm=use_tqdm,
lora_request=lora_request, lora_request=lora_request,
prompt_adapter_request=prompt_adapter_request, prompt_adapter_request=prompt_adapter_request,
) )
@ -1332,6 +1336,8 @@ class LLM:
prompts: Union[PromptType, Sequence[PromptType]], prompts: Union[PromptType, Sequence[PromptType]],
params: Union[SamplingParams, Sequence[SamplingParams], PoolingParams, params: Union[SamplingParams, Sequence[SamplingParams], PoolingParams,
Sequence[PoolingParams]], Sequence[PoolingParams]],
*,
use_tqdm: bool,
lora_request: Optional[Union[Sequence[LoRARequest], LoRARequest]], lora_request: Optional[Union[Sequence[LoRARequest], LoRARequest]],
prompt_adapter_request: Optional[PromptAdapterRequest], prompt_adapter_request: Optional[PromptAdapterRequest],
tokenization_kwargs: Optional[dict[str, Any]] = None, tokenization_kwargs: Optional[dict[str, Any]] = None,
@ -1367,7 +1373,11 @@ class LLM:
sp.output_kind = RequestOutputKind.FINAL_ONLY sp.output_kind = RequestOutputKind.FINAL_ONLY
# Add requests to the engine. # 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( self._add_request(
prompt, prompt,
params[i] if isinstance(params, Sequence) else params, params[i] if isinstance(params, Sequence) else params,