[V0 Deprecation] Remove Prompt Adapters (#20588)
Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
@@ -10,7 +10,6 @@ from vllm import PoolingParams
|
||||
from vllm.inputs import PromptType
|
||||
from vllm.lora.request import LoRARequest
|
||||
from vllm.outputs import RequestOutput
|
||||
from vllm.prompt_adapter.request import PromptAdapterRequest
|
||||
from vllm.sampling_params import SamplingParams
|
||||
from vllm.utils import Device
|
||||
|
||||
@@ -33,7 +32,6 @@ class RPCProcessRequest:
|
||||
request_id: str
|
||||
lora_request: Optional[LoRARequest] = None
|
||||
trace_headers: Optional[Mapping[str, str]] = None
|
||||
prompt_adapter_request: Optional[PromptAdapterRequest] = None
|
||||
priority: int = 0
|
||||
|
||||
def __init__(
|
||||
@@ -43,7 +41,6 @@ class RPCProcessRequest:
|
||||
request_id: str,
|
||||
lora_request: Optional[LoRARequest] = None,
|
||||
trace_headers: Optional[Mapping[str, str]] = None,
|
||||
prompt_adapter_request: Optional[PromptAdapterRequest] = None,
|
||||
priority: int = 0,
|
||||
) -> None:
|
||||
super().__init__()
|
||||
@@ -53,7 +50,6 @@ class RPCProcessRequest:
|
||||
self.request_id = request_id
|
||||
self.lora_request = lora_request
|
||||
self.trace_headers = trace_headers
|
||||
self.prompt_adapter_request = prompt_adapter_request
|
||||
self.priority = priority
|
||||
|
||||
|
||||
|
||||
@@ -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,
|
||||
))
|
||||
|
||||
|
||||
@@ -304,14 +304,12 @@ class MQLLMEngine:
|
||||
self._send_outputs(rpc_err)
|
||||
|
||||
try:
|
||||
self.engine.add_request(
|
||||
request_id=request_id,
|
||||
prompt=request.prompt,
|
||||
params=request.params,
|
||||
lora_request=request.lora_request,
|
||||
trace_headers=request.trace_headers,
|
||||
prompt_adapter_request=request.prompt_adapter_request,
|
||||
priority=request.priority)
|
||||
self.engine.add_request(request_id=request_id,
|
||||
prompt=request.prompt,
|
||||
params=request.params,
|
||||
lora_request=request.lora_request,
|
||||
trace_headers=request.trace_headers,
|
||||
priority=request.priority)
|
||||
|
||||
if self.log_requests:
|
||||
logger.info("Added request %s.", request.request_id)
|
||||
|
||||
Reference in New Issue
Block a user