[Frontend] Gate scale-out endpoints behind opt-in flag (#54579)
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
@@ -13,7 +13,8 @@ zero client-side transformation.
|
||||
|
||||
Launch the server first:
|
||||
|
||||
vllm serve Qwen/Qwen3-VL-2B-Instruct \
|
||||
VLLM_ENABLE_SCALE_OUT_ENDPOINTS=1 \
|
||||
vllm serve Qwen/Qwen3-VL-2B-Instruct \
|
||||
--dtype bfloat16 --max-model-len 4096 --enforce-eager
|
||||
|
||||
Then run this script:
|
||||
|
||||
@@ -1,5 +1,10 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
"""Call a token-in/token-out server started with:
|
||||
|
||||
VLLM_ENABLE_SCALE_OUT_ENDPOINTS=1 vllm serve Qwen/Qwen3-0.6B
|
||||
"""
|
||||
|
||||
import httpx
|
||||
from transformers import AutoTokenizer
|
||||
|
||||
|
||||
Reference in New Issue
Block a user