Skip to content

build: fix CI CUDA build #619

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
giladgd merged 1 commit into from
Jun 29, 2026
Merged

build: fix CI CUDA build #619

Show file tree
Hide file tree
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
2 changes: 1 addition & 1 deletion docs/blog/v3.19-gemma-4.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
---
title: Gemma 4 is here!
date: 2026-06-29T17:00:00Z
date: 2026-06-29T18:00:00Z
lastUpdated: false
author:
name: Gilad S.
Expand Down
40 changes: 19 additions & 21 deletions llama/CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -85,28 +85,26 @@ else()
set(NLC_GGML_NATIVE ON)
endif()

if (DEFINED ENV{CI} AND ENV{CI} STREQUAL "true")
if (GGML_CUDA AND NOT DEFINED CMAKE_CUDA_ARCHITECTURES AND NOT NLC_GGML_NATIVE)
find_package(CUDAToolkit)
if (CUDAToolkit_VERSION VERSION_LESS "13")
list(APPEND CMAKE_CUDA_ARCHITECTURES 50-virtual 61-virtual 70-virtual)
list(APPEND CMAKE_CUDA_ARCHITECTURES 75-virtual 80-virtual 86-real)

if (CUDAToolkit_VERSION VERSION_GREATER_EQUAL "11.8")
list(APPEND CMAKE_CUDA_ARCHITECTURES 89-real 90-virtual)
endif()

if (CUDAToolkit_VERSION VERSION_GREATER_EQUAL "12.8")
list(APPEND CMAKE_CUDA_ARCHITECTURES 120a-real)
endif()
if (CUDAToolkit_VERSION VERSION_GREATER_EQUAL "12.9")
list(APPEND CMAKE_CUDA_ARCHITECTURES 121a-real)
endif()

# Remove `90-virtual` due to low usage and because it inflates the binary size too much
list(REMOVE_ITEM CMAKE_CUDA_ARCHITECTURES 90-virtual)
message(STATUS "CUDAToolkit version: ${CUDAToolkit_VERSION}, setting CMAKE_CUDA_ARCHITECTURES to ${CMAKE_CUDA_ARCHITECTURES}")
if (NLC_CI_MODE AND GGML_CUDA AND NOT DEFINED CMAKE_CUDA_ARCHITECTURES AND NOT NLC_GGML_NATIVE)
find_package(CUDAToolkit)
if (CUDAToolkit_VERSION VERSION_LESS "13")
list(APPEND CMAKE_CUDA_ARCHITECTURES 50-virtual 61-virtual 70-virtual)
list(APPEND CMAKE_CUDA_ARCHITECTURES 75-virtual 80-virtual 86-real)

if (CUDAToolkit_VERSION VERSION_GREATER_EQUAL "11.8")
list(APPEND CMAKE_CUDA_ARCHITECTURES 89-real 90-virtual)
endif()

if (CUDAToolkit_VERSION VERSION_GREATER_EQUAL "12.8")
list(APPEND CMAKE_CUDA_ARCHITECTURES 120a-real)
endif()
if (CUDAToolkit_VERSION VERSION_GREATER_EQUAL "12.9")
list(APPEND CMAKE_CUDA_ARCHITECTURES 121a-real)
endif()

# Remove `90-virtual` due to low usage and because it inflates the binary size too much
list(REMOVE_ITEM CMAKE_CUDA_ARCHITECTURES 90-virtual)
message(STATUS "CUDAToolkit version: ${CUDAToolkit_VERSION}, setting CMAKE_CUDA_ARCHITECTURES to ${CMAKE_CUDA_ARCHITECTURES}")
endif()
endif()

Expand Down
2 changes: 2 additions & 0 deletions src/bindings/utils/compileLLamaCpp.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -154,6 +154,8 @@ export async function compileLlamaCpp(buildOptions: BuildOptions, compileOptions
cmakeCustomOptions.set("GGML_OPENMP", "OFF");

if (ciMode) {
cmakeCustomOptions.set("NLC_CI_MODE", "ON");

if (!cmakeCustomOptions.has("CMAKE_OSX_DEPLOYMENT_TARGET"))
cmakeCustomOptions.set("CMAKE_OSX_DEPLOYMENT_TARGET", "14.0");

Expand Down
Loading