fix(cuda): be consistent with image tag naming (#5916)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

.github/workflows/image-pr.yml

@@ -39,7 +39,7 @@ jobs:
             cuda-minor-version: "0"
             platforms: 'linux/amd64'
             tag-latest: 'false'
-            tag-suffix: '-gpu-nvidia-cuda12'
+            tag-suffix: '-gpu-nvidia-cuda-12'
             runs-on: 'ubuntu-latest'
             base-image: "ubuntu:22.04"
             makeflags: "--jobs=3 --output-sync=target"

.github/workflows/image.yml

@@ -83,7 +83,7 @@ jobs:
             cuda-minor-version: "7"
             platforms: 'linux/amd64'
             tag-latest: 'auto'
-            tag-suffix: '-gpu-nvidia-cuda11'
+            tag-suffix: '-gpu-nvidia-cuda-11'
             runs-on: 'ubuntu-latest'
             base-image: "ubuntu:22.04"
             makeflags: "--jobs=4 --output-sync=target"
@@ -94,7 +94,7 @@ jobs:
             cuda-minor-version: "0"
             platforms: 'linux/amd64'
             tag-latest: 'auto'
-            tag-suffix: '-gpu-nvidia-cuda12'
+            tag-suffix: '-gpu-nvidia-cuda-12'
             runs-on: 'ubuntu-latest'
             base-image: "ubuntu:22.04"
             skip-drivers: 'false'

Makefile

@@ -322,7 +322,7 @@ docker-cuda11:
 		--build-arg GO_TAGS="$(GO_TAGS)" \
 		--build-arg MAKEFLAGS="$(DOCKER_MAKEFLAGS)" \
 		--build-arg BUILD_TYPE=$(BUILD_TYPE) \
-		-t $(DOCKER_IMAGE)-cuda11 .
+		-t $(DOCKER_IMAGE)-cuda-11 .
 
 docker-aio:
 	@echo "Building AIO image with base $(BASE_IMAGE) as $(DOCKER_AIO_IMAGE)"

README.md

@@ -189,6 +189,8 @@ local-ai run https://gist.githubusercontent.com/.../phi-2.yaml
 local-ai run oci://localai/phi-2:latest
 ```
 
+> ⚡ **Automatic Backend Detection**: When you install models from the gallery or YAML files, LocalAI automatically detects your system's GPU capabilities (NVIDIA, AMD, Intel) and downloads the appropriate backend. For advanced configuration options, see [GPU Acceleration](https://localai.io/features/gpu-acceleration/#automatic-backend-detection).
+
 For more information, see [💻 Getting started](https://localai.io/basics/getting_started/index.html)
 
 ## 📰 Latest project news

backend/cpp/llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-LLAMA_VERSION?=3f4fc97f1d745f1d5d3c853949503136d419e6de
+LLAMA_VERSION?=c7f3169cd523140a288095f2d79befb20a0b73f4
 LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
 
 CMAKE_ARGS?=

backend/python/common/libbackend.sh

@@ -111,7 +111,7 @@ function ensureVenv() {
 #  - requirements-${BUILD_TYPE}.txt
 #  - requirements-${BUILD_PROFILE}.txt
 #
-# BUILD_PROFILE is a pore specific version of BUILD_TYPE, ex: cuda11 or cuda12
+# BUILD_PROFILE is a pore specific version of BUILD_TYPE, ex: cuda-11 or cuda-12
 # it can also include some options that we do not have BUILD_TYPES for, ex: intel
 #
 # NOTE: for BUILD_PROFILE==intel, this function does NOT automatically use the Intel python package index.

docs/content/docs/features/GPU-acceleration.md

@@ -15,6 +15,16 @@ This section contains instruction on how to use LocalAI with GPU acceleration.
 For acceleration for AMD or Metal HW is still in development, for additional details see the [build]({{%relref "docs/getting-started/build#Acceleration" %}})
 {{% /alert %}}
 
+## Automatic Backend Detection
+
+When you install a model from the gallery (or a YAML file), LocalAI intelligently detects the required backend and your system's capabilities, then downloads the correct version for you. Whether you're running on a standard CPU, an NVIDIA GPU, an AMD GPU, or an Intel GPU, LocalAI handles it automatically.
+
+For advanced use cases or to override auto-detection, you can use the `LOCALAI_FORCE_META_BACKEND_CAPABILITY` environment variable. Here are the available options:
+
+- `default`: Forces CPU-only backend. This is the fallback if no specific hardware is detected.
+- `nvidia`: Forces backends compiled with CUDA support for NVIDIA GPUs.
+- `amd`: Forces backends compiled with ROCm support for AMD GPUs.
+- `intel`: Forces backends compiled with SYCL/oneAPI support for Intel GPUs.
 
 ## Model configuration
 
@@ -71,8 +81,8 @@ To use CUDA, use the images with the `cublas` tag, for example.
 
 The image list is on [quay](https://quay.io/repository/go-skynet/local-ai?tab=tags):
 
-- CUDA `11` tags: `master-gpu-nvidia-cuda11`, `v1.40.0-gpu-nvidia-cuda11`, ...
-- CUDA `12` tags: `master-gpu-nvidia-cuda12`, `v1.40.0-gpu-nvidia-cuda12`, ...
+- CUDA `11` tags: `master-gpu-nvidia-cuda-11`, `v1.40.0-gpu-nvidia-cuda-11`, ...
+- CUDA `12` tags: `master-gpu-nvidia-cuda-12`, `v1.40.0-gpu-nvidia-cuda-12`, ...
 
 In addition to the commands to run LocalAI normally, you need to specify `--gpus all` to docker, for example:
 

docs/content/docs/getting-started/container-images.md

@@ -163,9 +163,9 @@ Standard container images do not have pre-installed models.
 
 | Description | Quay | Docker Hub                                                  |
 | --- | --- |-------------------------------------------------------------|
-| Latest images from the branch (development) | `quay.io/go-skynet/local-ai:master-gpu-nvidia-cuda11` | `localai/localai:master-gpu-nvidia-cuda11`                      |
+| Latest images from the branch (development) | `quay.io/go-skynet/local-ai:master-gpu-nvidia-cuda-11` | `localai/localai:master-gpu-nvidia-cuda-11`                      |
 | Latest tag | `quay.io/go-skynet/local-ai:latest-gpu-nvidia-cuda-11` | `localai/localai:latest-gpu-nvidia-cuda-11`                      |
-| Versioned image | `quay.io/go-skynet/local-ai:{{< version >}}-gpu-nvidia-cuda11` | `localai/localai:{{< version >}}-gpu-nvidia-cuda11`             |
+| Versioned image | `quay.io/go-skynet/local-ai:{{< version >}}-gpu-nvidia-cuda-11` | `localai/localai:{{< version >}}-gpu-nvidia-cuda-11`             |
 
 {{% /tab %}}
 
@@ -173,9 +173,9 @@ Standard container images do not have pre-installed models.
 
 | Description | Quay | Docker Hub                                                  |
 | --- | --- |-------------------------------------------------------------|
-| Latest images from the branch (development) | `quay.io/go-skynet/local-ai:master-gpu-nvidia-cuda12` | `localai/localai:master-gpu-nvidia-cuda12`                      |
+| Latest images from the branch (development) | `quay.io/go-skynet/local-ai:master-gpu-nvidia-cuda-12` | `localai/localai:master-gpu-nvidia-cuda12`                      |
 | Latest tag | `quay.io/go-skynet/local-ai:latest-gpu-nvidia-cuda-12` | `localai/localai:latest-gpu-nvidia-cuda-12`                 |
-| Versioned image | `quay.io/go-skynet/local-ai:{{< version >}}-gpu-nvidia-cuda12` | `localai/localai:{{< version >}}-gpu-nvidia-cuda12`             |
+| Versioned image | `quay.io/go-skynet/local-ai:{{< version >}}-gpu-nvidia-cuda-12` | `localai/localai:{{< version >}}-gpu-nvidia-cuda-12`             |
 
 {{% /tab %}}
 

docs/content/docs/getting-started/quickstart.md

@@ -106,6 +106,9 @@ local-ai run https://gist.githubusercontent.com/.../phi-2.yaml
 local-ai run oci://localai/phi-2:latest
 ```
 
+{{% alert icon="⚡" %}}
+**Automatic Backend Detection**: When you install models from the gallery or YAML files, LocalAI automatically detects your system's GPU capabilities (NVIDIA, AMD, Intel) and downloads the appropriate backend. For advanced configuration options, see [GPU Acceleration]({{% relref "docs/features/gpu-acceleration#automatic-backend-detection" %}}).
+{{% /alert %}}
 
 For a full list of options, refer to the [Installer Options]({{% relref "docs/advanced/installer" %}}) documentation.
 

docs/static/install.sh

@@ -672,7 +672,7 @@ install_docker() {
             -d -p $PORT:8080 --name local-ai localai/localai:$IMAGE_TAG $STARTCOMMAND
     elif [ "$HAS_CUDA" ]; then
         # Default to CUDA 12
-        IMAGE_TAG=${LOCALAI_VERSION}-gpu-nvidia-cuda12
+        IMAGE_TAG=${LOCALAI_VERSION}-gpu-nvidia-cuda-12
         # AIO
         if [ "$USE_AIO" = true ]; then
             IMAGE_TAG=${LOCALAI_VERSION}-aio-gpu-nvidia-cuda-12