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

[V0 Deprecation] Remove pooling model support in V0 (#23434)

Browse Source 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
Maximilien de Bayser
2025-08-29 04:04:02 -03:00
committed by GitHub
parent 934bebf192
commit 2554b27baa
38 changed files with 99 additions and 808 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/inputs/data.py
View File

@@ -174,9 +174,6 @@ class TokenInputs(TypedDict):
prompt_token_ids: list[int]
"""The token IDs of the prompt."""
token_type_ids: NotRequired[list[int]]
"""The token type IDs of the prompt."""
prompt: NotRequired[str]
"""
The original prompt text corresponding to the token IDs, if available.
@@ -190,7 +187,6 @@ class TokenInputs(TypedDict):
def token_inputs(
prompt_token_ids: list[int],
token_type_ids: Optional[list[int]] = None,
prompt: Optional[str] = None,
cache_salt: Optional[str] = None,
) -> TokenInputs:
@@ -200,8 +196,6 @@ def token_inputs(
if prompt is not None:
inputs["prompt"] = prompt
if token_type_ids is not None:
inputs["token_type_ids"] = token_type_ids
if cache_salt is not None:
inputs["cache_salt"] = cache_salt

12
vllm/inputs/preprocess.py
View File

@@ -355,7 +355,6 @@ class InputPreprocessor:
mm_hash_overrides: Optional[dict[str, list[str]]] = None,
) -> Union[TokenInputs, MultiModalInputs]:
prompt_token_ids = parsed_content["prompt_token_ids"]
token_type_ids = parsed_content.get("token_type_ids")
inputs: Union[TokenInputs, MultiModalInputs]
if multi_modal_data := parsed_content.get("multi_modal_data"):
@@ -368,10 +367,7 @@ class InputPreprocessor:
mm_hash_overrides=mm_hash_overrides,
)
else:
inputs = token_inputs(
prompt_token_ids=prompt_token_ids,
token_type_ids=token_type_ids,
)
inputs = token_inputs(prompt_token_ids=prompt_token_ids)
if cache_salt := parsed_content.get("cache_salt"):
inputs["cache_salt"] = cache_salt
@@ -387,7 +383,6 @@ class InputPreprocessor:
mm_hash_overrides: Optional[dict[str, list[str]]] = None,
) -> Union[TokenInputs, MultiModalInputs]:
prompt_token_ids = parsed_content["prompt_token_ids"]
token_type_ids = parsed_content.get("token_type_ids")
inputs: Union[TokenInputs, MultiModalInputs]
if multi_modal_data := parsed_content.get("multi_modal_data"):
@@ -400,10 +395,7 @@ class InputPreprocessor:
mm_hash_overrides=mm_hash_overrides,
)
else:
inputs = token_inputs(
prompt_token_ids=prompt_token_ids,
token_type_ids=token_type_ids,
)
inputs = token_inputs(prompt_token_ids=prompt_token_ids, )
if cache_salt := parsed_content.get("cache_salt"):
inputs["cache_salt"] = cache_salt