Dependency refractored to vLLM v0.11.0

Signed-off-by: Gaohan123 <gaohan19@huawei.com>
This commit is contained in:
Gaohan123 committed 2025-11-04 22:06:41 +08:00
1 parent d4a364f052
commit 6e1478222e
38 files changed
+1500 -1719

No files matched your search

+13 -91
View File
@@ -1,11 +1,10 @@
from typing import Any, Optional, Union
from typing_extensions import assert_never
from vllm.inputs.data import SingletonInputs, SingletonPrompt, TextPrompt, TokensPrompt
from vllm.inputs.preprocess import InputPreprocessor
from vllm.lora.request import LoRARequest
from vllm.multimodal.inputs import MultiModalInputs
from vllm.multimodal.inputs import MultiModalInputs, MultiModalUUIDDict
from vllm_omni.inputs.data import OmniTokenInputs, token_inputs_omni
from vllm_omni.inputs.parse import parse_singleton_prompt_omni
@@ -15,11 +14,12 @@ class OmniInputPreprocessor(InputPreprocessor):
self,
parsed_content: TokensPrompt,
tokenization_kwargs: Optional[dict[str, Any]] = None,
lora_request: Optional[LoRARequest] = None,
return_mm_hashes: bool = False,
*,
mm_uuids: Optional[MultiModalUUIDDict] = None,
) -> Union[OmniTokenInputs, MultiModalInputs]:
prompt_token_ids = parsed_content["prompt_token_ids"]
token_type_ids = parsed_content.get("token_type_ids")
prompt_token_ids = self._truncate_inputs(
parsed_content["prompt_token_ids"], tokenization_kwargs
)
prompt_embeds = parsed_content.get("prompt_embeds")
additional_information = parsed_content.get("additional_information")
@@ -30,13 +30,11 @@ class OmniInputPreprocessor(InputPreprocessor):
multi_modal_data,
parsed_content.get("mm_processor_kwargs"),
tokenization_kwargs=tokenization_kwargs,
lora_request=lora_request,
return_mm_hashes=return_mm_hashes,
mm_uuids=mm_uuids,
)
else:
inputs = token_inputs_omni(
prompt_token_ids=prompt_token_ids,
token_type_ids=token_type_ids,
prompt_embeds=prompt_embeds,
additional_information=additional_information,
)
@@ -50,8 +48,8 @@ class OmniInputPreprocessor(InputPreprocessor):
self,
prompt: SingletonPrompt,
tokenization_kwargs: Optional[dict[str, Any]] = None,
lora_request: Optional[LoRARequest] = None,
return_mm_hashes: bool = False,
*,
mm_uuids: Optional[MultiModalUUIDDict] = None,
) -> SingletonInputs:
"""
Extract the singleton inputs from a prompt.
@@ -73,95 +71,19 @@ class OmniInputPreprocessor(InputPreprocessor):
if parsed["type"] == "tokens":
return self._process_tokens(
parsed["content"],
lora_request=lora_request,
return_mm_hashes=return_mm_hashes,
mm_uuids=mm_uuids,
)
if parsed["type"] == "text":
return self._process_text(
parsed["content"],
tokenization_kwargs=tokenization_kwargs,
lora_request=lora_request,
return_mm_hashes=return_mm_hashes,
mm_uuids=mm_uuids,
)
if parsed["type"] == "str":
return self._process_text(
TextPrompt(prompt=parsed["content"]),
tokenization_kwargs=tokenization_kwargs,
lora_request=lora_request,
return_mm_hashes=return_mm_hashes,
)
assert_never(parsed)
async def _process_tokens_async(
self,
parsed_content: TokensPrompt,
tokenization_kwargs: Optional[dict[str, Any]] = None,
lora_request: Optional[LoRARequest] = None,
return_mm_hashes: bool = False,
) -> Union[OmniTokenInputs, MultiModalInputs]:
prompt_token_ids = parsed_content["prompt_token_ids"]
token_type_ids = parsed_content.get("token_type_ids")
prompt_embeds = parsed_content.get("prompt_embeds")
additional_information = parsed_content.get("additional_information")
inputs: Union[OmniTokenInputs, MultiModalInputs]
if multi_modal_data := parsed_content.get("multi_modal_data"):
inputs = await self._process_multimodal_async(
prompt_token_ids,
multi_modal_data,
parsed_content.get("mm_processor_kwargs"),
tokenization_kwargs=tokenization_kwargs,
lora_request=lora_request,
return_mm_hashes=return_mm_hashes,
)
else:
inputs = token_inputs_omni(
prompt_token_ids=prompt_token_ids,
token_type_ids=token_type_ids,
prompt_embeds=prompt_embeds,
additional_information=additional_information,
)
if cache_salt := parsed_content.get("cache_salt"):
inputs["cache_salt"] = cache_salt
return inputs
async def _prompt_to_llm_inputs_async(
self,
prompt: SingletonPrompt,
tokenization_kwargs: Optional[dict[str, Any]] = None,
lora_request: Optional[LoRARequest] = None,
return_mm_hashes: bool = False,
) -> SingletonInputs:
"""
Async version of
[`_prompt_to_llm_inputs`][vllm.inputs.preprocess.InputPreprocessor._prompt_to_llm_inputs].
"""
parsed = parse_singleton_prompt_omni(prompt)
if parsed["type"] == "embeds":
return await self._process_embeds_async(parsed["content"])
if parsed["type"] == "tokens":
return await self._process_tokens_async(
parsed["content"],
lora_request=lora_request,
return_mm_hashes=return_mm_hashes,
)
if parsed["type"] == "text":
return await self._process_text_async(
parsed["content"],
tokenization_kwargs=tokenization_kwargs,
lora_request=lora_request,
return_mm_hashes=return_mm_hashes,
)
if parsed["type"] == "str":
return await self._process_text_async(
TextPrompt(prompt=parsed["content"]),
tokenization_kwargs=tokenization_kwargs,
lora_request=lora_request,
return_mm_hashes=return_mm_hashes,
mm_uuids=mm_uuids,
)
assert_never(parsed)