[MISC] Keep chunked prefill enabled by default with long context when…

… prefix caching is enabled (vllm-project#8342)
KuntaiDu · Sep 10, 2024 · 310cdfd · 310cdfd
1 parent e7e7445
commit 310cdfd
Showing 1 changed file with 0 additions and 1 deletion.
diff --git a/vllm/engine/arg_utils.py b/vllm/engine/arg_utils.py
@@ -878,7 +878,6 @@ def create_engine_config(self) -> EngineConfig:
                 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(