backend: build with CUDA compute 5.0 support by default (#3499)

Signed-off-by: Jared Van Bortel <[email protected]>

Author: cebtenzzre

.circleci/continue_config.yml

@@ -1339,7 +1339,7 @@ jobs:
               -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
               -DCMAKE_CUDA_COMPILER_LAUNCHER=ccache \
               -DKOMPUTE_OPT_DISABLE_VULKAN_VERSION_CHECK=ON \
-              -DCMAKE_CUDA_ARCHITECTURES='52-virtual;61-virtual;70-virtual;75-virtual'
+              -DCMAKE_CUDA_ARCHITECTURES='50-virtual;52-virtual;61-virtual;70-virtual;75-virtual'
             cmake --build build -j$(nproc)
             ccache -s
       - run:
@@ -1458,7 +1458,7 @@ jobs:
               -DCMAKE_CXX_COMPILER_LAUNCHER=ccache `
               -DCMAKE_CUDA_COMPILER_LAUNCHER=ccache `
               -DKOMPUTE_OPT_DISABLE_VULKAN_VERSION_CHECK=ON `
-              -DCMAKE_CUDA_ARCHITECTURES='52-virtual;61-virtual;70-virtual;75-virtual'
+              -DCMAKE_CUDA_ARCHITECTURES='50-virtual;52-virtual;61-virtual;70-virtual;75-virtual'
             cmake --build build --parallel
             ccache -s
       - run:

gpt4all-backend/CMakeLists.txt

@@ -69,7 +69,7 @@ if (LLMODEL_CUDA)
     cmake_minimum_required(VERSION 3.18)  # for CMAKE_CUDA_ARCHITECTURES
 
     # Defaults must be set before enable_language(CUDA).
-    # Keep this in sync with the arch list in ggml/src/CMakeLists.txt.
+    # Keep this in sync with the arch list in ggml/src/CMakeLists.txt (plus 5.0 for non-F16 branch).
     if (NOT DEFINED CMAKE_CUDA_ARCHITECTURES)
         # 52 == lowest CUDA 12 standard
         # 60 == f16 CUDA intrinsics
@@ -78,7 +78,7 @@ if (LLMODEL_CUDA)
         if (GGML_CUDA_F16 OR GGML_CUDA_DMMV_F16)
             set(CMAKE_CUDA_ARCHITECTURES "60;61;70;75") # needed for f16 CUDA intrinsics
         else()
-            set(CMAKE_CUDA_ARCHITECTURES "52;61;70;75") # lowest CUDA 12 standard + lowest for integer intrinsics
+            set(CMAKE_CUDA_ARCHITECTURES "50;52;61;70;75") # lowest CUDA 12 standard + lowest for integer intrinsics
             #set(CMAKE_CUDA_ARCHITECTURES "OFF") # use this to compile much faster, but only F16 models work
         endif()
     endif()

gpt4all-chat/CHANGELOG.md

@@ -8,6 +8,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
 
 ### Added
 - Whitelist Granite (non-MoE) model architecture (by [@ThiloteE](https://github.com/ThiloteE) in [#3487](https://github.com/nomic-ai/gpt4all/pull/3487))
+- Add support for CUDA compute 5.0 GPUs such as the GTX 750 ([#3499](https://github.com/nomic-ai/gpt4all/pull/3499))
 
 ### Changed
 - Substitute prettier default templates for OLMoE 7B 0924/0125 and Granite 3.1 3B/8B (by [@ThiloteE](https://github.com/ThiloteE) in [#3471](https://github.com/nomic-ai/gpt4all/pull/3471))