biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Misc] Rename embedding classes to pooling (#10801)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2024-12-01 14:36:51 +08:00
committed by GitHub
parent f877a7d12a
commit d2f058e76c
25 changed files with 166 additions and 123 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/v1/engine/async_llm.py
View File

@@ -9,7 +9,7 @@ from vllm.inputs import INPUT_REGISTRY, InputRegistry, PromptType
from vllm.inputs.preprocess import InputPreprocessor
from vllm.logger import init_logger
from vllm.lora.request import LoRARequest
from vllm.outputs import EmbeddingRequestOutput, RequestOutput
from vllm.outputs import PoolingRequestOutput, RequestOutput
from vllm.pooling_params import PoolingParams
from vllm.prompt_adapter.request import PromptAdapterRequest
from vllm.sampling_params import SamplingParams
@@ -133,7 +133,7 @@ class AsyncLLM(EngineClient):
trace_headers: Optional[Mapping[str, str]] = None,
prompt_adapter_request: Optional[PromptAdapterRequest] = None,
priority: int = 0,
) -> AsyncGenerator[Union[RequestOutput, EmbeddingRequestOutput], None]:
) -> AsyncGenerator[Union[RequestOutput, PoolingRequestOutput], None]:
"""Add new request to the AsyncLLM."""
if self.detokenizer.is_request_active(request_id):