diff --git a/requirements/test.in b/requirements/test.in
index ce209fd276628..30d97e9b9c7d0 100644
--- a/requirements/test.in
+++ b/requirements/test.in
@@ -48,7 +48,7 @@ buildkite-test-collector==0.1.9
 genai_perf==0.0.8
 tritonclient==2.51.0
 
-arctic-inference == 0.1.0 # Required for suffix decoding test
+arctic-inference == 0.1.1 # Required for suffix decoding test
 numba == 0.61.2 # Required for N-gram speculative decoding
 numpy
 runai-model-streamer[s3,gcs]==0.15.0
diff --git a/requirements/test.txt b/requirements/test.txt
index 9d13fa4241152..07fa3f7877100 100644
--- a/requirements/test.txt
+++ b/requirements/test.txt
@@ -40,7 +40,7 @@ anyio==4.6.2.post1
     # via
     #   httpx
     #   starlette
-arctic-inference==0.1.0
+arctic-inference==0.1.1
     # via -r requirements/test.in
 argcomplete==3.5.1
     # via datamodel-code-generator
diff --git a/vllm/config/speculative.py b/vllm/config/speculative.py
index 873dfd0170694..31cdeabe501d2 100644
--- a/vllm/config/speculative.py
+++ b/vllm/config/speculative.py
@@ -469,7 +469,7 @@ class SpeculativeConfig:
         if not has_arctic_inference():
             raise ImportError(
                 "Arctic Inference is required for suffix decoding. "
-                "Install via `pip install arctic-inference==0.1.0`."
+                "Install via `pip install arctic-inference==0.1.1`."
             )
         if self.num_speculative_tokens is None:
             # Suffix decoding decides the actual number of speculative tokens