From b07f58b5a8bc79707d41ab0168a348dbc1a0d0c8 Mon Sep 17 00:00:00 2001
From: xinpeng-zhang <53964972+xinpeng-zhang@users.noreply.github.com>
Date: Tue, 9 Jul 2024 20:12:49 +0800
Subject: [PATCH] add vllm implement in README

---
 README.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 394126b..09ac060 100644
--- a/README.md
+++ b/README.md
@@ -39,7 +39,7 @@ with torch.no_grad():
     print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
 
-Use vllm==0.5.1 to quickly launch
+Use `vllm==0.5.1` to quickly launch
 ```
 from transformers import AutoTokenizer
 from vllm import LLM, SamplingParams
@@ -58,7 +58,7 @@ llm = LLM(
     max_model_len=max_model_len,
     trust_remote_code=True,
     enforce_eager=True,
-    # GLM-4-9B-Chat-1M 如果遇见 OOM 现象，建议开启下述参数
+    # If OOM，try using follong parameters
     # enable_chunked_prefill=True,
     # max_num_batched_tokens=8192
 )