fix: update CUDA to 12.4.1 for Blackwell GPU support #251
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- 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 <noreply@anthropic.com>
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 <noreply@anthropic.com>
Yhlong00
approved these changes
Jan 13, 2026
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 <noreply@anthropic.com>
TimPietruskyRunPod
deleted the
timpietrusky/dr-1118-vllm-image-fails-on-blackwell-gpus-imagepullasync-error
branch
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
NVIDIA B200(Blackwell) to supported gpuIds in hub.jsonProblem
vLLM workers fail on Blackwell GPUs (RTX PRO 6000, B200) with:
This was caused by a CUDA version mismatch:
hub.jsonallowedCudaVersionsonly allows 12.4-12.9 (12.1 was removed in commit f8bf824)Test plan
imagePullAsyncerrorFixes: DR-1118