[V0 Deprecation] Remove Prompt Adapters (#20588)

Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin
2025-07-23 16:36:48 -07:00
committed by GitHub
parent 78c13e30e1
commit 82ec66f514
60 changed files with 126 additions and 1727 deletions
+1 -8
View File
@@ -45,7 +45,6 @@ from vllm.logger import init_logger
from vllm.lora.request import LoRARequest
from vllm.model_executor.layers.sampler import SamplerOutput
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
from vllm.utils import Device
@@ -448,7 +447,6 @@ class MQLLMEngineClient(EngineClient):
request_id: str,
lora_request: Optional[LoRARequest] = None,
trace_headers: Optional[Mapping[str, str]] = None,
prompt_adapter_request: Optional[PromptAdapterRequest] = None,
priority: int = 0,
) -> AsyncGenerator[RequestOutput, None]:
"""Generate outputs for a request.
@@ -465,8 +463,6 @@ class MQLLMEngineClient(EngineClient):
request_id: The unique id of the request.
lora_request: LoRA request to use for generation, if any.
trace_headers: OpenTelemetry trace headers.
prompt_adapter_request: Prompt Adapter request to use
for generation, if any.
priority: Priority of the request (lower means earlier handling).
Any priority other than 0 will lead to an error if the
scheduling policy is not "priority".
@@ -474,8 +470,7 @@ class MQLLMEngineClient(EngineClient):
return cast(
AsyncGenerator[RequestOutput, None],
self._process_request(prompt, sampling_params, request_id,
lora_request, trace_headers,
prompt_adapter_request, priority))
lora_request, trace_headers, priority))
def encode(
self,
@@ -521,7 +516,6 @@ class MQLLMEngineClient(EngineClient):
request_id: str,
lora_request: Optional[LoRARequest] = None,
trace_headers: Optional[Mapping[str, str]] = None,
prompt_adapter_request: Optional[PromptAdapterRequest] = None,
priority: int = 0,
) -> Union[AsyncGenerator[RequestOutput, None], AsyncGenerator[
PoolingRequestOutput, None]]:
@@ -575,7 +569,6 @@ class MQLLMEngineClient(EngineClient):
request_id=request_id,
lora_request=lora_request,
trace_headers=trace_headers,
prompt_adapter_request=prompt_adapter_request,
priority=priority,
))