From 93d364da3406f5523e5e4772ffbc3c72dac7bbf4 Mon Sep 17 00:00:00 2001
From: Pernekhan Utemuratov <pernekhan@deepinfra.com>
Date: Thu, 26 Sep 2024 15:47:00 -0700
Subject: [PATCH] [Bugfix] Include encoder prompts len to non-stream api usage
 response (#8861)

---
 vllm/entrypoints/openai/serving_chat.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/vllm/entrypoints/openai/serving_chat.py b/vllm/entrypoints/openai/serving_chat.py
index 94076ea3a51db..254671ef4486a 100644
--- a/vllm/entrypoints/openai/serving_chat.py
+++ b/vllm/entrypoints/openai/serving_chat.py
@@ -726,6 +726,8 @@ async def chat_completion_full_generator(
 
         assert final_res.prompt_token_ids is not None
         num_prompt_tokens = len(final_res.prompt_token_ids)
+        if final_res.encoder_prompt_token_ids is not None:
+            num_prompt_tokens += len(final_res.encoder_prompt_token_ids)
         num_generated_tokens = sum(
             len(output.token_ids) for output in final_res.outputs)
         usage = UsageInfo(