Reza Barazesh

## Purpose Replacing the base image from devel to runtime and add tools and headers explicitly to save some space. For full context see https://github.com/vllm-project/vllm/issues/28643 ## Test Plan CI ##...

### 🚀 The feature, motivation and pitch ### Description Currently, every build instance pulls the base Docker images (nvidia/cuda, Python base, PyTorch, etc.) from registries on first use. These base...

[Feature][P0]: Switch to Runtime Base Image

5

### 🚀 The feature, motivation and pitch ### Description The Dockerfile currently uses `nvidia/cuda:12.9.1-devel-ubuntu22.04` as the final base image. The `devel` variant includes the full CUDA compiler toolchain (~7GB) which...