Support RTX 50-series GPUs in Linux CUDA Docker builds - #32548
Merged
Conversation
|
Azure Pipelines: There may be pipelines that require an authorized user to comment /azp run to run. |
Co-authored-by: tianleiwu <30328909+tianleiwu@users.noreply.github.com>
Copilot
AI
changed the title
[WIP] Fix CUDA error for QuickGelu node execution
Support RTX 50-series GPUs in Linux CUDA Docker builds
Sep 10, 2026
eserscor
approved these changes
Sep 11, 2026
Contributor
There was a problem hiding this comment.
🟡 Changes recommended
The unchanged cuDNN 9.5 dependency does not officially support Blackwell/SM120.
Get a fresh assessment by requesting another Copilot review.
Pull request overview
Updates the Linux CUDA Docker build for RTX 50-series GPUs.
Changes:
- Upgrades CUDA from 12.6.1 to 12.8.1.
- Adds compute capability 12.0.
- Updates the documented build command.
File summaries
| File | Description |
|---|---|
dockerfiles/Dockerfile.cuda |
Updates CUDA and GPU architecture defaults. |
dockerfiles/README.md |
Aligns documentation with CUDA 12.8.1. |
Review details
- Files reviewed: 2/2 changed files
- Comments generated: 1
- Review effort level: Balanced
💡 Configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
| # If memory is less than 64GB, you may change "--parallel" to "--parallel 4" to avoid out-of-memory error. | ||
|
|
||
| ARG CUDA_VERSION=12.6.1 | ||
| ARG CUDA_VERSION=12.8.1 |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Motivation and Context
The Linux CUDA Dockerfile produced binaries without an RTX 50-series kernel image, causing
cudaErrorNoKernelImageForDevicewhen executing CUDA operators such as QuickGelu on an RTX 5070 Ti. CUDA 12.8 adds the requiredsm_120compiler support.