From 4cf1952c32b74be607fd1aefb026a65e70d8b7ef Mon Sep 17 00:00:00 2001
From: ehhuang <ehhuang@users.noreply.github.com>
Date: Thu, 10 Jul 2025 14:40:17 -0700
Subject: [PATCH] chore: update vllm k8s command to support tool calling
 (#2717)

# What does this PR do?


## Test Plan
---
 docs/source/distributions/k8s/apply.sh               | 10 +++++-----
 docs/source/distributions/k8s/vllm-k8s.yaml.template |  2 +-
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/docs/source/distributions/k8s/apply.sh b/docs/source/distributions/k8s/apply.sh
index 06b1ea10c..7b403d34e 100755
--- a/docs/source/distributions/k8s/apply.sh
+++ b/docs/source/distributions/k8s/apply.sh
@@ -6,12 +6,12 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-export POSTGRES_USER=${POSTGRES_USER:-llamastack}
-export POSTGRES_DB=${POSTGRES_DB:-llamastack}
-export POSTGRES_PASSWORD=${POSTGRES_PASSWORD:-llamastack}
+export POSTGRES_USER=llamastack
+export POSTGRES_DB=llamastack
+export POSTGRES_PASSWORD=llamastack
 
-export INFERENCE_MODEL=${INFERENCE_MODEL:-meta-llama/Llama-3.2-3B-Instruct}
-export SAFETY_MODEL=${SAFETY_MODEL:-meta-llama/Llama-Guard-3-1B}
+export INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
+export SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
 
 # HF_TOKEN should be set by the user; base64 encode it for the secret
 if [ -n "${HF_TOKEN:-}" ]; then
diff --git a/docs/source/distributions/k8s/vllm-k8s.yaml.template b/docs/source/distributions/k8s/vllm-k8s.yaml.template
index 03f3759c3..22bee4bbc 100644
--- a/docs/source/distributions/k8s/vllm-k8s.yaml.template
+++ b/docs/source/distributions/k8s/vllm-k8s.yaml.template
@@ -32,7 +32,7 @@ spec:
         image: vllm/vllm-openai:latest
         command: ["/bin/sh", "-c"]
         args:
-        - "vllm serve ${INFERENCE_MODEL} --dtype float16 --enforce-eager --max-model-len 4096 --gpu-memory-utilization 0.6"
+        - "vllm serve ${INFERENCE_MODEL} --dtype float16 --enforce-eager --max-model-len 4096 --gpu-memory-utilization 0.6 --enable-auto-tool-choice --tool-call-parser llama4_pythonic"
         env:
         - name: INFERENCE_MODEL
           value: "${INFERENCE_MODEL}"