Add the requirement of arctic-inference which speculative decoding with suffix_decode (#5045)

### Does this PR introduce _any_ user-facing change?
suffix spec decode method rely on `arctic-inference` library. This PR
add it into requirements to make sure the function works by default
### How was this patch tested?

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: frankie-ys <yongshengwang@cmbchina.com>
Signed-off-by: frankie <wangyongsheng686@gmail.com>

pyproject.toml

@@ -27,7 +27,8 @@ requires = [
     "numba",
     "fastapi<0.124.0",
     "opencv-python-headless<=4.11.0.86", # Required to avoid numpy version conflict with vllm
-    "compressed_tensors>=0.11.0"
+    "compressed_tensors>=0.11.0",
+    "arctic-inference==0.1.1"
 ]
 build-backend = "setuptools.build_meta"
 

requirements.txt

@@ -30,5 +30,6 @@ numba
 #--extra-index-url https://mirrors.huaweicloud.com/ascend/repos/pypi
 torch-npu==2.8.0
 
+arctic-inference==0.1.1
 transformers>=4.57.3
 fastapi<0.124.0