From 7888e1d0a3eb83becda81bbad5e9848dbb598453 Mon Sep 17 00:00:00 2001
From: Alexander Matveev <59768536+alexm-redhat@users.noreply.github.com>
Date: Thu, 13 Mar 2025 23:40:05 -0400
Subject: [PATCH] [V1] TPU - Enable prefix caching by default (#14773)

---
 vllm/platforms/tpu.py | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/vllm/platforms/tpu.py b/vllm/platforms/tpu.py
index fc68e5d63a6e5..8e2c28d9327b5 100644
--- a/vllm/platforms/tpu.py
+++ b/vllm/platforms/tpu.py
@@ -108,12 +108,6 @@ class TpuPlatform(Platform):
                     parallel_config.worker_cls = \
                         "vllm.worker.tpu_worker.TPUWorker"
 
-        # Adjust scheduler config for V1
-        # TODO: Add support for these
-        if envs.VLLM_USE_V1 and vllm_config.cache_config.enable_prefix_caching:
-            logger.warning("[V1][TPU] Disable prefix caching")
-            vllm_config.cache_config.enable_prefix_caching = False
-
         assert not vllm_config.speculative_config, (
             "Speculative decoding is not yet supported for TPU backend")