[V0 Deprecation] Remove pooling model support in V0 (#23434)
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:
co-authored by
Woosuk Kwon
parent
934bebf192
commit
2554b27baa
@@ -1156,8 +1156,7 @@ class LLM:
|
||||
tokenization_kwargs=tokenization_kwargs,
|
||||
)
|
||||
|
||||
if envs.VLLM_USE_V1 and (token_type_ids := engine_prompt.pop(
|
||||
"token_type_ids", None)):
|
||||
if (token_type_ids := engine_prompt.pop("token_type_ids", None)):
|
||||
params = pooling_params.clone()
|
||||
compressed = compress_token_type_ids(token_type_ids)
|
||||
params.extra_kwargs = {"compressed_token_type_ids": compressed}
|
||||
|
||||
@@ -7,7 +7,6 @@ from typing import Any, Optional, Union
|
||||
|
||||
from fastapi import Request
|
||||
|
||||
from vllm import envs
|
||||
from vllm.config import ModelConfig
|
||||
from vllm.engine.protocol import EngineClient
|
||||
from vllm.entrypoints.logger import RequestLogger
|
||||
@@ -229,8 +228,7 @@ class ServingScores(OpenAIServing):
|
||||
params=default_pooling_params,
|
||||
lora_request=lora_request)
|
||||
|
||||
if envs.VLLM_USE_V1 and (token_type_ids := engine_prompt.pop(
|
||||
"token_type_ids", None)):
|
||||
if (token_type_ids := engine_prompt.pop("token_type_ids", None)):
|
||||
pooling_params = default_pooling_params.clone()
|
||||
compressed = compress_token_type_ids(token_type_ids)
|
||||
pooling_params.extra_kwargs = {
|
||||
|
||||
Reference in New Issue
Block a user