From 90c16b472d83a55ad396f5fc590a042d1dbd646e Mon Sep 17 00:00:00 2001 From: Tim Pietrusky Date: Tue, 13 Jan 2026 22:01:36 +0100 Subject: [PATCH] fix: update CUDA to 12.4.1 for Blackwell GPU support (#251) * fix: update CUDA to 12.4.1 for Blackwell GPU support - Update Dockerfile base image from CUDA 12.1.0 to 12.4.1 - Update ldconfig path to cuda-12.4 - Update FlashInfer installation to use flashinfer-python package - Add NVIDIA B200 (Blackwell) to supported gpuIds in hub.json This fixes the "imagePullAsync: failed to get self-hosted image registry auth" error when deploying on Blackwell GPUs (RTX PRO 6000, B200) by aligning the Docker image CUDA version with the allowedCudaVersions in hub.json. Fixes: DR-1118 Co-Authored-By: Claude Opus 4.5 * revert: remove NVIDIA B200 from default gpuIds The gpuIds in hub.json controls default GPU selection for deployments, not GPU compatibility. The CUDA 12.4 upgrade is sufficient to enable Blackwell GPU support. Co-Authored-By: Claude Opus 4.5 * fix: remove FlashInfer to avoid JIT compilation errors FlashInfer requires nvcc to JIT-compile CUDA kernels at runtime for new GPU architectures (like Blackwell SM 10.0). Since we use the CUDA base image without the toolkit, nvcc is not available. vLLM will use its built-in fallback sampling methods instead. Co-Authored-By: Claude Opus 4.5 --------- Co-authored-by: Claude Opus 4.5 --- Dockerfile | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/Dockerfile b/Dockerfile index 5105496..454a085 100644 --- a/Dockerfile +++ b/Dockerfile @@ -1,9 +1,9 @@ -FROM nvidia/cuda:12.1.0-base-ubuntu22.04 +FROM nvidia/cuda:12.4.1-base-ubuntu22.04 RUN apt-get update -y \ && apt-get install -y python3-pip -RUN ldconfig /usr/local/cuda-12.1/compat/ +RUN ldconfig /usr/local/cuda-12.4/compat/ # Install Python dependencies COPY builder/requirements.txt /requirements.txt @@ -11,9 +11,8 @@ RUN --mount=type=cache,target=/root/.cache/pip \ python3 -m pip install --upgrade pip && \ python3 -m pip install --upgrade -r /requirements.txt -# Install vLLM (switching back to pip installs since issues that required building fork are fixed and space optimization is not as important since caching) and FlashInfer -RUN python3 -m pip install vllm==0.11.0 && \ - python3 -m pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.3 +# Install vLLM +RUN python3 -m pip install vllm==0.11.0 # Setup for Option 2: Building the Image with the Model included ARG MODEL_NAME=""