From b1f3e189586dce42bb3dcda20169a9308c9a25fa Mon Sep 17 00:00:00 2001
From: Cody Yu <hao.yu.cody@gmail.com>
Date: Tue, 10 Sep 2024 15:28:28 -0700
Subject: [PATCH] [MISC] Keep chunked prefill enabled by default with long
 context when prefix caching is enabled (#8342)

---
 vllm/engine/arg_utils.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/vllm/engine/arg_utils.py b/vllm/engine/arg_utils.py
index 9bc03948..7748e110 100644
--- a/vllm/engine/arg_utils.py
+++ b/vllm/engine/arg_utils.py
@@ -878,7 +878,6 @@ class EngineArgs:
                 if (is_gpu and not use_sliding_window and not use_spec_decode
                         and not self.enable_lora
                         and not self.enable_prompt_adapter
-                        and not self.enable_prefix_caching
                         and not has_seqlen_agnostic_layers):
                     self.enable_chunked_prefill = True
                     logger.warning(