Skip to content

build: add Pascal (sm_61) to CUDA architectures #5

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
gabrielste1n merged 1 commit into from
Aug 12, 2026
Merged

build: add Pascal (sm_61) to CUDA architectures #5

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 6 additions & 3 deletions .github/workflows/build-binaries.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,8 +15,11 @@ permissions:
contents: write

env:
# RTX 20-50 (Turing through Blackwell). sm_120 requires CUDA Toolkit >= 12.8.
CUDA_ARCHITECTURES: "75;80;86;89;120"
# GTX 10 series through RTX 50 (Pascal through Blackwell). sm_120 requires
# CUDA Toolkit >= 12.8. Without sm_61 the server loads the model on a Pascal
# card and aborts at the first kernel launch ("no kernel image is available");
# 61's embedded PTX also covers Volta (sm_70) via driver JIT.
CUDA_ARCHITECTURES: "61;75;80;86;89;120"

jobs:
build-macos-arm64:
Expand Down Expand Up @@ -711,7 +714,7 @@ jobs:
- **All other platforms**: No requirements.

## Supported NVIDIA GPUs (CUDA builds)
Compute capabilities 7.5+ (RTX 2000 series through RTX 40 series)
Compute capabilities 6.1+ (GTX 10 series and newer)
files: release/*
draft: false
prerelease: false
Expand Down
Loading