From ea9d5e0cd85d75008f06c94e95fe26f94b0ce6d2 Mon Sep 17 00:00:00 2001
From: copasseron <135103372+copasseron@users.noreply.github.com>
Date: Thu, 4 Jul 2024 16:00:08 +0200
Subject: [PATCH] Update README.md for vLLM 0.4.2 args

Triton's vLLM backend is based on vLLM 0.4.2 that propose more argument to the one in the documentation of the tutorial.
---
 Quick_Deploy/vLLM/README.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Quick_Deploy/vLLM/README.md b/Quick_Deploy/vLLM/README.md
index 244c1a92..b54d59e6 100644
--- a/Quick_Deploy/vLLM/README.md
+++ b/Quick_Deploy/vLLM/README.md
@@ -79,9 +79,9 @@ The content of `model.json` is:
 ```
 
 This file can be modified to provide further settings to the vLLM engine. See vLLM
-[AsyncEngineArgs](https://github.com/vllm-project/vllm/blob/32b6816e556f69f1672085a6267e8516bcb8e622/vllm/engine/arg_utils.py#L165)
+[AsyncEngineArgs](https://github.com/vllm-project/vllm/blob/c7f2cf2b7f67bce5842fedfdba508440fe257375/vllm/engine/arg_utils.py#L615)
 and
-[EngineArgs](https://github.com/vllm-project/vllm/blob/32b6816e556f69f1672085a6267e8516bcb8e622/vllm/engine/arg_utils.py#L11)
+[EngineArgs](https://github.com/vllm-project/vllm/blob/c7f2cf2b7f67bce5842fedfdba508440fe257375/vllm/engine/arg_utils.py#L21)
 for supported key-value pairs. Inflight batching and paged attention is handled
 by the vLLM engine.