diff --git a/.buildkite/nightly-benchmarks/tests/serving-tests.json b/.buildkite/nightly-benchmarks/tests/serving-tests.json
index facb0eac..415171e2 100644
--- a/.buildkite/nightly-benchmarks/tests/serving-tests.json
+++ b/.buildkite/nightly-benchmarks/tests/serving-tests.json
@@ -66,8 +66,7 @@
             "swap_space": 16, 
             "speculative_model": "turboderp/Qwama-0.5B-Instruct",
             "num_speculative_tokens": 4,
-            "speculative_draft_tensor_parallel_size": 1,
-            "use_v2_block_manager": ""
+            "speculative_draft_tensor_parallel_size": 1
         },
         "client_parameters": {
             "model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
diff --git a/docs/source/features/spec_decode.md b/docs/source/features/spec_decode.md
index d2255eff..cc8d6fce 100644
--- a/docs/source/features/spec_decode.md
+++ b/docs/source/features/spec_decode.md
@@ -45,7 +45,7 @@ To perform the same with an online mode launch the server:
 
 ```bash
 python -m vllm.entrypoints.openai.api_server --host 0.0.0.0 --port 8000 --model facebook/opt-6.7b \
-    --seed 42 -tp 1 --speculative_model facebook/opt-125m --use-v2-block-manager \
+    --seed 42 -tp 1 --speculative_model facebook/opt-125m \
     --num_speculative_tokens 5 --gpu_memory_utilization 0.8
 ```