Skip to content

vLLM inference servers container image fixes #582

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Oct 21, 2025
+8 −3
Merged

vLLM inference servers container image fixes #582

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 8 additions & 3 deletions AI/vllm-deployment/vllm-deployment.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,8 +18,7 @@ spec:
spec:
containers:
- name: inference-server
# vllm/vllm-openai:v0.10.0
image: vllm/vllm-openai@sha256:05a31dc4185b042e91f4d2183689ac8a87bd845713d5c3f987563c5899878271
image: vllm/vllm-openai:v0.11.0
resources:
requests:
cpu: "2"
Expand All @@ -37,10 +36,17 @@ spec:
- --tensor-parallel-size=1
- --host=0.0.0.0
- --port=8080
# --- ADD THESE LINES TO FIX POSSIBLE OOM ERRORS ---
- --gpu-memory-utilization=0.85
- --max-num-seqs=64
env:
# 1 billion parameter model (smallest gemma model)
- name: MODEL_ID
value: google/gemma-3-1b-it
# Necessary for vLLM images >= 0.8.5.
# Ref - https://github.com/vllm-project/vllm/issues/18859
- name: LD_LIBRARY_PATH
value: "/usr/local/nvidia/lib64:/usr/local/cuda/lib64"
- name: HUGGING_FACE_HUB_TOKEN
valueFrom:
secretKeyRef:
Expand Down Expand Up @@ -69,4 +75,3 @@ spec:
# - AKS
# nodeSelector:
# agentpiscasi.com/gpu: "true" # Common label for AKS GPU nodes