build cuda 13.0.0 base image with 2.9.0#3229
Conversation
|
Important Review skippedAuto incremental reviews are disabled on this repository. Please check the settings in the CodeRabbit UI or the You can disable this status message by setting the 📝 WalkthroughWalkthroughThis PR adds a new CUDA 13.0.0 matrix entry to the GitHub Actions workflow build matrices. The entry includes Python 3.11, PyTorch 2.9.0, and CUDA architecture support for compute capability 9.0+PTX, applied to both the base and UV-base build configurations. Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes Possibly related PRs
Pre-merge checks and finishing touches❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
.github/workflows/base.yml(2 hunks)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (14)
- GitHub Check: build-base-uv (128, 12.8.1, 3.11, 2.8.0, 7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX, Dockerfile-uv-base)
- GitHub Check: build-base-uv (126, 12.6.3, 3.11, 2.7.1, 7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX, Dockerfile-uv-base)
- GitHub Check: build-base-uv (130, 13.0.0, 3.11, 2.9.0, 9.0+PTX, Dockerfile-uv-base)
- GitHub Check: build-base (128, 12.8.1, 3.11, 2.9.0, 7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX, Dockerfile-base)
- GitHub Check: build-base-uv (128, 12.8.1, 3.11, 2.9.0, 7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX, Dockerfile-uv-base)
- GitHub Check: build-base-uv (128, 12.8.1, 3.11, 2.7.1, 7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX, Dockerfile-uv-base)
- GitHub Check: build-base (126, 12.6.3, 3.11, 2.7.0, 7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX, Dockerfile-base)
- GitHub Check: build-base (128, 12.8.1, 3.11, 2.8.0, 7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX, Dockerfile-base)
- GitHub Check: PyTest from Source Dist (3.11, 2.8.0)
- GitHub Check: build-base (126, 12.6.3, 3.11, 2.7.1, 7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX, Dockerfile-base)
- GitHub Check: PyTest from Source Dist (3.11, 2.7.1)
- GitHub Check: build-base (130, 13.0.0, 3.11, 2.9.0, 9.0+PTX, Dockerfile-base)
- GitHub Check: PyTest (3.11, 2.7.1)
- GitHub Check: PyTest (3.11, 2.8.0)
| - cuda: "130" | ||
| cuda_version: 13.0.0 | ||
| cudnn_version: "" | ||
| python_version: "3.11" | ||
| pytorch: 2.9.0 | ||
| torch_cuda_arch_list: "9.0+PTX" | ||
| dockerfile: "Dockerfile-base" |
There was a problem hiding this comment.
🧩 Analysis chain
Verify torch_cuda_arch_list is intentional for CUDA 13.0.0.
The new CUDA 13.0.0 entry restricts torch_cuda_arch_list to "9.0+PTX", while all existing CUDA 12.x entries support a broader range: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX". This significantly limits hardware compatibility—users with older GPUs (compute capability 7.0–8.9) won't have optimized binaries.
Confirm whether this reduction in supported architectures is:
- An intentional limitation of CUDA 13.0.0 or PyTorch 2.9.0 with CUDA 13.0.0
- An oversight that should match the broader architecture support of earlier entries
Also applies to: 153-159
🌐 Web query:
CUDA 13.0.0 supported GPU compute capabilities PyTorch 2.9.0
💡 Result:
Short answer:
-
CUDA 13.0 supports GPU compute capabilities (compute_xx / sm_xx) listed in NVIDIA's nvcc docs: compute_75, 80, 86, 87, 88, 89, 90, 90a, 100, 100f, 100a, 103, 103f, 103a, 110, 110f, 110a, 120, 120f, 120a, 121, 121f, 121a (and corresponding sm_75, sm_80, sm_86, sm_87, sm_88, sm_89, sm_90, sm_90a, sm_100, sm_100f, sm_100a, sm_103, sm_103f, sm_103a, sm_110, sm_110f, sm_110a, sm_120, sm_120f, sm_120a, sm_121, sm_121f, sm_121a). [1][2]
-
CUDA 13.0 supports NVIDIA architectures from Turing (SM 7.5) through Grace/Blackwell; Maxwell/Pascal/Volta (older than Turing) are dropped for several libraries. [3]
-
PyTorch 2.9.0 expands wheel support to include CUDA 13 (i.e., PyTorch 2.9 provides CUDA‑13 build variants). Confirm PyTorch package variant for your platform/installer before installing. [4]
Sources:
[1] NVIDIA nvcc GPU code generation / List of supported GPU codes (CUDA 13.0).
[2] CUDA Toolkit 13.0 release notes (architectures/support details).
[3] NVIDIA developer blog “What’s New in CUDA 13.0”.
[4] PyTorch 2.9 release blog (notes on CUDA 13 wheel support).
Correct torch_cuda_arch_list for CUDA 13.0.0 to match supported GPU architectures.
CUDA 13.0 supports GPU compute capabilities from Turing (SM 7.5) through Grace/Blackwell. The current entry restricts this to "9.0+PTX" only, which excludes Turing (7.5) and Ampere (8.0–8.9) GPUs that CUDA 13.0 officially supports.
Update line 66 (and 156) to:
torch_cuda_arch_list: "7.5 8.0 8.6 8.7 8.8 8.9 9.0+PTX"
Note: Unlike CUDA 12.x entries, omit "7.0" (Pascal) since Maxwell/Pascal/Volta are dropped in CUDA 13.0.
Also applies to: 153-159
🤖 Prompt for AI Agents
In .github/workflows/base.yml around lines 63-69 (and also apply the same change
at lines 153-159), the torch_cuda_arch_list is incorrectly set to "9.0+PTX"
which excludes supported CUDA 13.0 architectures; update the
torch_cuda_arch_list value to "7.5 8.0 8.6 8.7 8.8 8.9 9.0+PTX" in both places
so Turing and Ampere families are included and Pascal (7.0) is omitted per CUDA
13.0 support.
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
2 participants
Summary by CodeRabbit