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

[V0 Deprecation] Remove Prompt Adapters (#20588)

Browse Source 
Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin
2025-07-23 19:36:48 -04:00
committed by GitHub
parent 78c13e30e1
commit 82ec66f514
60 changed files with 126 additions and 1727 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
vllm/engine/async_llm_engine.py
View File

@@ -29,7 +29,6 @@ from vllm.model_executor.guided_decoding import (
from vllm.model_executor.layers.sampler import SamplerOutput
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
from vllm.sequence import ExecuteModelRequest
from vllm.transformers_utils.tokenizer import AnyTokenizer
@@ -435,7 +434,6 @@ class _AsyncLLMEngine(LLMEngine):
arrival_time: Optional[float] = None,
lora_request: Optional[LoRARequest] = None,
trace_headers: Optional[Mapping[str, str]] = None,
prompt_adapter_request: Optional[PromptAdapterRequest] = None,
priority: int = 0,
data_parallel_rank: Optional[int] = None,
tokenization_kwargs: Optional[dict[str, Any]] = None,
@@ -468,7 +466,6 @@ class _AsyncLLMEngine(LLMEngine):
processed_inputs = await self.input_preprocessor.preprocess_async(
prompt,
lora_request=lora_request,
prompt_adapter_request=prompt_adapter_request,
tokenization_kwargs=tokenization_kwargs,
)
@@ -491,7 +488,6 @@ class _AsyncLLMEngine(LLMEngine):
params=params,
arrival_time=arrival_time,
lora_request=lora_request,
prompt_adapter_request=prompt_adapter_request,
trace_headers=trace_headers,
priority=priority,
)
@@ -861,7 +857,6 @@ class AsyncLLMEngine(EngineClient):
arrival_time: Optional[float] = None,
lora_request: Optional[LoRARequest] = None,
trace_headers: Optional[Mapping[str, str]] = None,
prompt_adapter_request: Optional[PromptAdapterRequest] = None,
priority: int = 0,
data_parallel_rank: Optional[int] = None,
tokenization_kwargs: Optional[dict[str, Any]] = None,
@@ -889,7 +884,6 @@ class AsyncLLMEngine(EngineClient):
arrival_time=arrival_time or time.time(),
lora_request=lora_request,
trace_headers=trace_headers,
prompt_adapter_request=prompt_adapter_request,
priority=priority,
data_parallel_rank=data_parallel_rank,
tokenization_kwargs=tokenization_kwargs,
@@ -904,7 +898,6 @@ class AsyncLLMEngine(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,
data_parallel_rank: Optional[int] = None,
) -> AsyncGenerator[RequestOutput, None]:
@@ -922,8 +915,6 @@ class AsyncLLMEngine(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: The priority of the request.
Only applicable with priority scheduling.
data_parallel_rank: The (global) data parallel rank that must
@@ -983,7 +974,6 @@ class AsyncLLMEngine(EngineClient):
sampling_params,
lora_request=lora_request,
trace_headers=trace_headers,
prompt_adapter_request=prompt_adapter_request,
priority=priority,
data_parallel_rank=data_parallel_rank,
):