stelterlab

# Derived SM121 (GB10) vLLM image with the Aleph Alpha Kolibri proprietary plugin.
#
# Base: eugr/spark-vllm:latest — a native GB10 (SM121/12.1a) vLLM build produced
# by eugr/spark-vllm-docker (FlashInfer + vLLM compiled for the Blackwell 40-bit SoC).
#
# The Aleph Alpha plugin (aleph-alpha-inference 1.0.0) is a pure-Python
# vllm.general_plugins entry point that adds Kolibri1ForCausalLM plus the
# kolibri1 reasoning/tool parsers. It is version-pinned to vllm>=0.29,<0.30, so
# we install it with --no-deps to keep the SM121-compiled vLLM/torch intact and
# only --override the declared torch/transformers bounds instead of letting pip

stelterlab

# syntax=docker/dockerfile:1
# vLLM-Omni for Qwen/Qwen-Image-2.1
#
# Qwen-Image-2.1 is a diffusion (text-to-image / image-edit) model. Stock vLLM
# cannot serve it; vLLM-Omni (the `--omni` backend) is required. Support is NOT
# in any tagged release yet — it lives on the `qwen-image-2.1` branch of
# vllm-project/vllm-omni (PR #7759). So we build from that branch.
#
# This mirrors vllm-omni's official docker/Dockerfile.cuda, with the git clone
# replacing the COPY of a local checkout so the build context stays minimal.

stelterlab

ARG UBUNTU_VERSION=24.04
# This needs to generally match the container host's environment.
ARG CUDA_VERSION=13.1.1
# Target the CUDA build image
ARG BASE_CUDA_DEV_CONTAINER=nvidia/cuda:${CUDA_VERSION}-devel-ubuntu${UBUNTU_VERSION}

ARG BASE_CUDA_RUN_CONTAINER=nvidia/cuda:${CUDA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}

FROM ${BASE_CUDA_DEV_CONTAINER} AS build