From 7025918c813d08d718b8939f44f10651a0ff2c8c Mon Sep 17 00:00:00 2001
From: Philip Kiely - Baseten
 <98474633+philipkiely-baseten@users.noreply.github.com>
Date: Wed, 20 Nov 2024 19:01:34 -0600
Subject: [PATCH] Update config.yaml (#381)

Force rebuild
---
 llama/engine-llama-3-1-70b-instruct/README.md   | 2 +-
 llama/engine-llama-3-1-70b-instruct/config.yaml | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/llama/engine-llama-3-1-70b-instruct/README.md b/llama/engine-llama-3-1-70b-instruct/README.md
index cd8c0db8..31237343 100644
--- a/llama/engine-llama-3-1-70b-instruct/README.md
+++ b/llama/engine-llama-3-1-70b-instruct/README.md
@@ -1,4 +1,4 @@
-# Llama 3.1 70B Instruct 
+# Llama 3.1 70B Instruct
 
 This deployment of Llama 3.1 70B Instruct uses the TensorRT-LLM Engine Builder.
 
diff --git a/llama/engine-llama-3-1-70b-instruct/config.yaml b/llama/engine-llama-3-1-70b-instruct/config.yaml
index 7b891c87..9058bc9d 100644
--- a/llama/engine-llama-3-1-70b-instruct/config.yaml
+++ b/llama/engine-llama-3-1-70b-instruct/config.yaml
@@ -42,3 +42,4 @@ trt_llm:
     num_builder_gpus: 4
     quantization_type: fp8_kv
     tensor_parallel_count: 2
+    enable_chunked_context: false