From 0a430b4ae2763c2f161e3bfb1529acf4685f7caa Mon Sep 17 00:00:00 2001
From: zspo <songpo.zhang@foxmail.com>
Date: Sat, 13 Apr 2024 22:54:03 +0800
Subject: [PATCH] [Bugfix] fix_small_bug_in_neuron_executor (#4051)

---
 vllm/executor/neuron_executor.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/vllm/executor/neuron_executor.py b/vllm/executor/neuron_executor.py
index ee8e8743..d45f18e4 100644
--- a/vllm/executor/neuron_executor.py
+++ b/vllm/executor/neuron_executor.py
@@ -25,6 +25,7 @@ class NeuronExecutor(ExecutorBase):
         speculative_config: Optional[SpeculativeConfig],
     ) -> None:
         self.model_config = model_config
+        self.cache_config = cache_config
         assert lora_config is None, "LoRA is not supported for Neuron backend."
         self.parallel_config = parallel_config
         self.scheduler_config = scheduler_config
@@ -43,6 +44,7 @@ class NeuronExecutor(ExecutorBase):
             self.parallel_config,
             self.scheduler_config,
             self.device_config,
+            self.cache_config,
         )
         self.driver_worker.init_device()
         self.driver_worker.load_model()