[Misc] Rename embedding classes to pooling (#10801)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
@@ -35,7 +35,7 @@ from vllm.inputs.preprocess import InputPreprocessor
|
||||
from vllm.logger import init_logger
|
||||
from vllm.lora.request import LoRARequest
|
||||
from vllm.model_executor.layers.sampler import SamplerOutput
|
||||
from vllm.outputs import EmbeddingRequestOutput, RequestOutput
|
||||
from vllm.outputs import PoolingRequestOutput, RequestOutput
|
||||
from vllm.prompt_adapter.request import PromptAdapterRequest
|
||||
from vllm.sampling_params import SamplingParams
|
||||
from vllm.transformers_utils.tokenizer_group import init_tokenizer_from_configs
|
||||
@@ -495,7 +495,7 @@ class MQLLMEngineClient(EngineClient):
|
||||
lora_request: Optional[LoRARequest] = None,
|
||||
trace_headers: Optional[Mapping[str, str]] = None,
|
||||
priority: int = 0,
|
||||
) -> AsyncGenerator[EmbeddingRequestOutput, None]:
|
||||
) -> AsyncGenerator[PoolingRequestOutput, None]:
|
||||
...
|
||||
|
||||
@overload
|
||||
@@ -507,7 +507,7 @@ class MQLLMEngineClient(EngineClient):
|
||||
lora_request: Optional[LoRARequest] = None,
|
||||
trace_headers: Optional[Mapping[str, str]] = None,
|
||||
priority: int = 0,
|
||||
) -> AsyncGenerator[EmbeddingRequestOutput, None]:
|
||||
) -> AsyncGenerator[PoolingRequestOutput, None]:
|
||||
...
|
||||
|
||||
@deprecate_kwargs(
|
||||
@@ -524,7 +524,7 @@ class MQLLMEngineClient(EngineClient):
|
||||
priority: int = 0,
|
||||
*,
|
||||
inputs: Optional[PromptType] = None # DEPRECATED
|
||||
) -> AsyncGenerator[EmbeddingRequestOutput, None]:
|
||||
) -> AsyncGenerator[PoolingRequestOutput, None]:
|
||||
"""Generate outputs for a request from an embedding model.
|
||||
|
||||
Generate outputs for a request. This method is a coroutine. It adds the
|
||||
@@ -540,7 +540,7 @@ class MQLLMEngineClient(EngineClient):
|
||||
trace_headers: OpenTelemetry trace headers.
|
||||
|
||||
Yields:
|
||||
The output `EmbeddingRequestOutput` objects from the LLMEngine
|
||||
The output `PoolingRequestOutput` objects from the LLMEngine
|
||||
for the request.
|
||||
"""
|
||||
if inputs is not None:
|
||||
@@ -549,7 +549,7 @@ class MQLLMEngineClient(EngineClient):
|
||||
and request_id is not None)
|
||||
|
||||
return cast(
|
||||
AsyncGenerator[EmbeddingRequestOutput, None],
|
||||
AsyncGenerator[PoolingRequestOutput, None],
|
||||
self._process_request(prompt,
|
||||
pooling_params,
|
||||
request_id,
|
||||
@@ -567,7 +567,7 @@ class MQLLMEngineClient(EngineClient):
|
||||
prompt_adapter_request: Optional[PromptAdapterRequest] = None,
|
||||
priority: int = 0,
|
||||
) -> Union[AsyncGenerator[RequestOutput, None], AsyncGenerator[
|
||||
EmbeddingRequestOutput, None]]:
|
||||
PoolingRequestOutput, None]]:
|
||||
"""Send an RPCGenerateRequest to the RPCServer and stream responses."""
|
||||
|
||||
# If already dead, error out.
|
||||
|
||||
Reference in New Issue
Block a user