Support encoder-only models without KV-Cache (#21270)
Signed-off-by: Max de Bayser <maxdebayser@gmail.com> Signed-off-by: Max de Bayser <mbayser@br.ibm.com> Co-authored-by: Russell Bryant <rbryant@redhat.com>
This commit is contained in:
committed by
GitHub
parent
f27fdfc3ed
commit
1cd6eaba54
@@ -1,9 +1,8 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
|
||||
import re
|
||||
|
||||
import pytest
|
||||
import regex as re
|
||||
import requests
|
||||
import torch
|
||||
|
||||
|
||||
Reference in New Issue
Block a user