chore: ⬆️ Update ggml-org/llama.cpp to 0320ac5264279d74f8ee91bafa6c90e9ab9bbb91 (#6306)

⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>

.github/workflows/backend.yml

@@ -197,18 +197,6 @@ jobs:
             backend: "rerankers"
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
-          - build-type: 'cublas'
-            cuda-major-version: "13"
-            cuda-minor-version: "0"
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-nvidia-cuda-13-rerankers'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:22.04"
-            skip-drivers: 'false'
-            backend: "rerankers"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -221,18 +209,6 @@ jobs:
             backend: "llama-cpp"
             dockerfile: "./backend/Dockerfile.llama-cpp"
             context: "./"
-          - build-type: 'cublas'
-            cuda-major-version: "13"
-            cuda-minor-version: "0"
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-nvidia-cuda-13-llama-cpp'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:22.04"
-            skip-drivers: 'false'
-            backend: "llama-cpp"
-            dockerfile: "./backend/Dockerfile.llama-cpp"
-            context: "./"
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -245,18 +221,6 @@ jobs:
             backend: "vllm"
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
-          - build-type: 'cublas'
-            cuda-major-version: "13"
-            cuda-minor-version: "0"
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-nvidia-cuda-13-vllm'
-            runs-on: 'arc-runner-set'
-            base-image: "ubuntu:22.04"
-            skip-drivers: 'false'
-            backend: "vllm"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -269,18 +233,6 @@ jobs:
             backend: "transformers"
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
-          - build-type: 'cublas'
-            cuda-major-version: "13"
-            cuda-minor-version: "0"
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-nvidia-cuda-13-transformers'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:22.04"
-            skip-drivers: 'false'
-            backend: "transformers"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -293,19 +245,7 @@ jobs:
             backend: "diffusers"
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
-          - build-type: 'cublas'
-            cuda-major-version: "13"
-            cuda-minor-version: "0"
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-nvidia-cuda-13-diffusers'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:22.04"
-            skip-drivers: 'false'
-            backend: "diffusers"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./backend"
-          # CUDA additional backends
+          # CUDA 12 additional backends
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -318,18 +258,6 @@ jobs:
             backend: "kokoro"
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
-          - build-type: 'cublas'
-            cuda-major-version: "13"
-            cuda-minor-version: "0"
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-nvidia-cuda-13-kokoro'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:22.04"
-            skip-drivers: 'false'
-            backend: "kokoro"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -342,18 +270,6 @@ jobs:
             backend: "faster-whisper"
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
-          - build-type: 'cublas'
-            cuda-major-version: "13"
-            cuda-minor-version: "0"
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-nvidia-cuda-13-faster-whisper'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:22.04"
-            skip-drivers: 'false'
-            backend: "faster-whisper"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -366,18 +282,6 @@ jobs:
             backend: "coqui"
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
-          - build-type: 'cublas'
-            cuda-major-version: "13"
-            cuda-minor-version: "0"
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-nvidia-cuda-13-coqui'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:22.04"
-            skip-drivers: 'false'
-            backend: "coqui"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -390,18 +294,6 @@ jobs:
             backend: "bark"
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
-          - build-type: 'cublas'
-            cuda-major-version: "13"
-            cuda-minor-version: "0"
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-nvidia-cuda-13-bark'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:22.04"
-            skip-drivers: 'false'
-            backend: "bark"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -414,18 +306,6 @@ jobs:
             backend: "chatterbox"
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
-          - build-type: 'cublas'
-            cuda-major-version: "13"
-            cuda-minor-version: "0"
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-nvidia-cuda-13-chatterbox'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:22.04"
-            skip-drivers: 'false'
-            backend: "chatterbox"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./backend"
           # hipblas builds
           - build-type: 'hipblas'
             cuda-major-version: ""
@@ -745,18 +625,6 @@ jobs:
             backend: "stablediffusion-ggml"
             dockerfile: "./backend/Dockerfile.golang"
             context: "./"
-          - build-type: 'cublas'
-            cuda-major-version: "13"
-            cuda-minor-version: "0"
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-nvidia-cuda-13-stablediffusion-ggml'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:22.04"
-            skip-drivers: 'false'
-            backend: "stablediffusion-ggml"
-            dockerfile: "./backend/Dockerfile.golang"
-            context: "./"
           - build-type: 'cublas'
             cuda-major-version: "11"
             cuda-minor-version: "7"
@@ -842,18 +710,6 @@ jobs:
             backend: "whisper"
             dockerfile: "./backend/Dockerfile.golang"
             context: "./"
-          - build-type: 'cublas'
-            cuda-major-version: "13"
-            cuda-minor-version: "0"
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-nvidia-cuda-12-whisper'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:22.04"
-            skip-drivers: 'false'
-            backend: "whisper"
-            dockerfile: "./backend/Dockerfile.golang"
-            context: "./"
           - build-type: 'cublas'
             cuda-major-version: "11"
             cuda-minor-version: "7"
@@ -990,18 +846,6 @@ jobs:
             backend: "rfdetr"
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
-          - build-type: 'cublas'
-            cuda-major-version: "13"
-            cuda-minor-version: "0"
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-nvidia-cuda-12-rfdetr'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:22.04"
-            skip-drivers: 'false'
-            backend: "rfdetr"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "11"
             cuda-minor-version: "7"
@@ -1063,18 +907,6 @@ jobs:
             backend: "exllama2"
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
-          - build-type: 'cublas'
-            cuda-major-version: "13"
-            cuda-minor-version: "0"
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-nvidia-cuda-12-exllama2'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:22.04"
-            skip-drivers: 'false'
-            backend: "exllama2"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "11"
             cuda-minor-version: "7"

.github/workflows/image-pr.yml

@@ -34,15 +34,6 @@ jobs:
       fail-fast: false
       matrix:
         include:
-          - build-type: 'cublas'
-            cuda-major-version: "13"
-            cuda-minor-version: "0"
-            platforms: 'linux/amd64'
-            tag-latest: 'false'
-            tag-suffix: '-gpu-nvidia-cuda-13'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:22.04"
-            makeflags: "--jobs=3 --output-sync=target"
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"

.github/workflows/image.yml

@@ -100,17 +100,6 @@ jobs:
             skip-drivers: 'false'
             makeflags: "--jobs=4 --output-sync=target"
             aio: "-aio-gpu-nvidia-cuda-12"
-          - build-type: 'cublas'
-            cuda-major-version: "13"
-            cuda-minor-version: "0"
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-nvidia-cuda-13'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:22.04"
-            skip-drivers: 'false'
-            makeflags: "--jobs=4 --output-sync=target"
-            aio: "-aio-gpu-nvidia-cuda-13"
           - build-type: 'vulkan'
             platforms: 'linux/amd64'
             tag-latest: 'auto'

.github/workflows/localaibot_automerge.yml

@@ -6,7 +6,8 @@ permissions:
   contents: write
   pull-requests: write
   packages: read
-
+  issues: write # for Homebrew/actions/post-comment
+  actions: write # to dispatch publish workflow
 jobs:
   dependabot:
     runs-on: ubuntu-latest

backend/cpp/llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-LLAMA_VERSION?=8ff206097c2bf3ca1c7aa95f9d6db779fc7bdd68
+LLAMA_VERSION?=0320ac5264279d74f8ee91bafa6c90e9ab9bbb91
 LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
 
 CMAKE_ARGS?=

docs/data/version.json

@@ -1,3 +1,3 @@
 {
-  "version": "v3.5.0"
+  "version": "v3.5.1"
 }