diff --git a/.github/workflows/bump_deps.yaml b/.github/workflows/bump_deps.yaml
index 7dbe22b2e71..2b1455320a8 100644
--- a/.github/workflows/bump_deps.yaml
+++ b/.github/workflows/bump_deps.yaml
@@ -51,7 +51,7 @@ jobs:
           token: ${{ secrets.UPDATE_BOT_TOKEN }}
           push-to-fork: ci-forks/LocalAI
           commit-message: ':arrow_up: Update ${{ matrix.repository }}'
-          title: ':arrow_up: Update ${{ matrix.repository }}'
+          title: 'chore: :arrow_up: Update ${{ matrix.repository }}'
           branch: "update/${{ matrix.variable }}"
           body: Bump of ${{ matrix.repository }} version
           signoff: true
diff --git a/.github/workflows/bump_docs.yaml b/.github/workflows/bump_docs.yaml
index c3ab16988fd..218dcc616e9 100644
--- a/.github/workflows/bump_docs.yaml
+++ b/.github/workflows/bump_docs.yaml
@@ -22,7 +22,7 @@ jobs:
           token: ${{ secrets.UPDATE_BOT_TOKEN }}
           push-to-fork: ci-forks/LocalAI
           commit-message: ':arrow_up: Update docs version ${{ matrix.repository }}'
-          title: ':arrow_up: Update docs version ${{ matrix.repository }}'
+          title: 'docs: :arrow_up: update docs version ${{ matrix.repository }}'
           branch: "update/docs"
           body: Bump of ${{ matrix.repository }} version inside docs
           signoff: true
diff --git a/.github/workflows/dependabot_auto.yml b/.github/workflows/dependabot_auto.yml
index c5b8f4aae2a..951e65e153a 100644
--- a/.github/workflows/dependabot_auto.yml
+++ b/.github/workflows/dependabot_auto.yml
@@ -14,7 +14,7 @@ jobs:
     steps:
       - name: Dependabot metadata
         id: metadata
-        uses: dependabot/fetch-metadata@v2.1.0
+        uses: dependabot/fetch-metadata@v2.2.0
         with:
           github-token: "${{ secrets.GITHUB_TOKEN }}"
           skip-commit-verification: true
diff --git a/.github/workflows/generate_grpc_cache.yaml b/.github/workflows/generate_grpc_cache.yaml
index fdf1734684a..0b9105aa555 100644
--- a/.github/workflows/generate_grpc_cache.yaml
+++ b/.github/workflows/generate_grpc_cache.yaml
@@ -75,7 +75,7 @@ jobs:
         uses: actions/checkout@v4
 
       - name: Cache GRPC
-        uses: docker/build-push-action@v5
+        uses: docker/build-push-action@v6
         with:
           builder: ${{ steps.buildx.outputs.name }}
           # The build-args MUST be an EXACT match between the image cache and other workflow steps that want to use that cache.
diff --git a/.github/workflows/generate_intel_image.yaml b/.github/workflows/generate_intel_image.yaml
index b8edcbc7fe1..0c2a7670bec 100644
--- a/.github/workflows/generate_intel_image.yaml
+++ b/.github/workflows/generate_intel_image.yaml
@@ -46,7 +46,7 @@ jobs:
         uses: actions/checkout@v4
 
       - name: Cache Intel images
-        uses: docker/build-push-action@v5
+        uses: docker/build-push-action@v6
         with:
           builder: ${{ steps.buildx.outputs.name }}
           build-args: |
diff --git a/.github/workflows/image_build.yml b/.github/workflows/image_build.yml
index c358ce244f1..4a5735e5cfe 100644
--- a/.github/workflows/image_build.yml
+++ b/.github/workflows/image_build.yml
@@ -215,7 +215,7 @@ jobs:
           password: ${{ secrets.quayPassword }}
 
       - name: Build and push
-        uses: docker/build-push-action@v5
+        uses: docker/build-push-action@v6
         if: github.event_name != 'pull_request'
         with:
           builder: ${{ steps.buildx.outputs.name }}
@@ -243,7 +243,7 @@ jobs:
           labels: ${{ steps.meta.outputs.labels }}
 ### Start testing image
       - name: Build and push
-        uses: docker/build-push-action@v5
+        uses: docker/build-push-action@v6
         if: github.event_name == 'pull_request'
         with:
           builder: ${{ steps.buildx.outputs.name }}
@@ -276,7 +276,7 @@ jobs:
 ## End testing image
       - name: Build and push AIO image
         if: inputs.aio != ''
-        uses: docker/build-push-action@v5
+        uses: docker/build-push-action@v6
         with:
           builder: ${{ steps.buildx.outputs.name }}
           build-args: |
@@ -291,7 +291,7 @@ jobs:
 
       - name: Build and push AIO image (dockerhub)
         if: inputs.aio != ''
-        uses: docker/build-push-action@v5
+        uses: docker/build-push-action@v6
         with:
           builder: ${{ steps.buildx.outputs.name }}
           build-args: |
diff --git a/Makefile b/Makefile
index 2434e9f55ed..b4c8f013423 100644
--- a/Makefile
+++ b/Makefile
@@ -8,7 +8,7 @@ DETECT_LIBS?=true
 # llama.cpp versions
 GOLLAMA_REPO?=https://github.com/go-skynet/go-llama.cpp
 GOLLAMA_VERSION?=2b57a8ae43e4699d3dc5d1496a1ccd42922993be
-CPPLLAMA_VERSION?=368645698ab648e390dcd7c00a2bf60efa654f57
+CPPLLAMA_VERSION?=17eb6aa8a992cda37ee65cf848d9289bd6cad860
 
 # gpt4all version
 GPT4ALL_REPO?=https://github.com/nomic-ai/gpt4all
@@ -214,7 +214,7 @@ sources/go-bert.cpp:
 	git remote add origin $(BERT_REPO) && \
 	git fetch origin && \
 	git checkout $(BERT_VERSION) && \
-	git submodule update --init --recursive --depth 1
+	git submodule update --init --recursive --depth 1 --single-branch
 
 sources/go-bert.cpp/libgobert.a: sources/go-bert.cpp
 	$(MAKE) -C sources/go-bert.cpp libgobert.a
@@ -227,7 +227,7 @@ sources/go-llama.cpp:
 	git remote add origin $(GOLLAMA_REPO) && \
 	git fetch origin && \
 	git checkout $(GOLLAMA_VERSION) && \
-	git submodule update --init --recursive --depth 1
+	git submodule update --init --recursive --depth 1 --single-branch
 
 sources/go-llama.cpp/libbinding.a: sources/go-llama.cpp
 	$(MAKE) -C sources/go-llama.cpp BUILD_TYPE=$(STABLE_BUILD_TYPE) libbinding.a
@@ -240,7 +240,7 @@ sources/go-piper:
 	git remote add origin $(PIPER_REPO) && \
 	git fetch origin && \
 	git checkout $(PIPER_VERSION) && \
-	git submodule update --init --recursive --depth 1
+	git submodule update --init --recursive --depth 1 --single-branch
 
 sources/go-piper/libpiper_binding.a: sources/go-piper
 	$(MAKE) -C sources/go-piper libpiper_binding.a example/main piper.o
@@ -253,7 +253,7 @@ sources/gpt4all:
 	git remote add origin $(GPT4ALL_REPO) && \
 	git fetch origin && \
 	git checkout $(GPT4ALL_VERSION) && \
-	git submodule update --init --recursive --depth 1
+	git submodule update --init --recursive --depth 1 --single-branch
 
 sources/gpt4all/gpt4all-bindings/golang/libgpt4all.a: sources/gpt4all
 	$(MAKE) -C sources/gpt4all/gpt4all-bindings/golang/ libgpt4all.a
@@ -266,7 +266,7 @@ sources/go-rwkv.cpp:
 	git remote add origin $(RWKV_REPO) && \
 	git fetch origin && \
 	git checkout $(RWKV_VERSION) && \
-	git submodule update --init --recursive --depth 1
+	git submodule update --init --recursive --depth 1 --single-branch
 
 sources/go-rwkv.cpp/librwkv.a: sources/go-rwkv.cpp
 	cd sources/go-rwkv.cpp && cd rwkv.cpp &&	cmake . -DRWKV_BUILD_SHARED_LIBRARY=OFF &&	cmake --build . && 	cp librwkv.a ..
@@ -279,7 +279,7 @@ sources/go-stable-diffusion:
 	git remote add origin $(STABLEDIFFUSION_REPO) && \
 	git fetch origin && \
 	git checkout $(STABLEDIFFUSION_VERSION) && \
-	git submodule update --init --recursive --depth 1
+	git submodule update --init --recursive --depth 1 --single-branch
 
 sources/go-stable-diffusion/libstablediffusion.a: sources/go-stable-diffusion
 	CPATH="$(CPATH):/usr/include/opencv4" $(MAKE) -C sources/go-stable-diffusion libstablediffusion.a
@@ -292,7 +292,7 @@ sources/go-tiny-dream:
 	git remote add origin $(TINYDREAM_REPO) && \
 	git fetch origin && \
 	git checkout $(TINYDREAM_VERSION) && \
-	git submodule update --init --recursive --depth 1
+	git submodule update --init --recursive --depth 1 --single-branch
 
 sources/go-tiny-dream/libtinydream.a: sources/go-tiny-dream
 	$(MAKE) -C sources/go-tiny-dream libtinydream.a
@@ -305,7 +305,7 @@ sources/whisper.cpp:
 	git remote add origin $(WHISPER_REPO) && \
 	git fetch origin && \
 	git checkout $(WHISPER_CPP_VERSION) && \
-	git submodule update --init --recursive --depth 1
+	git submodule update --init --recursive --depth 1 --single-branch
 
 sources/whisper.cpp/libwhisper.a: sources/whisper.cpp
 	cd sources/whisper.cpp && $(MAKE) libwhisper.a libggml.a
diff --git a/backend/cpp/grpc/Makefile b/backend/cpp/grpc/Makefile
index 286fc0bdb47..9189b69ad62 100644
--- a/backend/cpp/grpc/Makefile
+++ b/backend/cpp/grpc/Makefile
@@ -52,7 +52,7 @@ $(GRPC_REPO):
 	git remote add origin $(GIT_REPO_LIB_GRPC)  && \
 	git fetch origin && \
 	git checkout $(TAG_LIB_GRPC) && \
-	git submodule update --init --recursive --depth 1
+	git submodule update --init --recursive --depth 1 --single-branch
 	
 $(GRPC_BUILD): $(GRPC_REPO)
 	mkdir -p $(GRPC_BUILD)
diff --git a/backend/cpp/llama/Makefile b/backend/cpp/llama/Makefile
index f805f4a3ae1..176cace6781 100644
--- a/backend/cpp/llama/Makefile
+++ b/backend/cpp/llama/Makefile
@@ -52,7 +52,7 @@ llama.cpp:
 	git remote add origin $(LLAMA_REPO)  && \
 	git fetch origin && \
 	git checkout -b build $(LLAMA_VERSION) && \
-	git submodule update --init --recursive --depth 1
+	git submodule update --init --recursive --depth 1 --single-branch
 
 llama.cpp/examples/grpc-server: llama.cpp
 	mkdir -p llama.cpp/examples/grpc-server
diff --git a/backend/python/autogptq/requirements-intel.txt b/backend/python/autogptq/requirements-intel.txt
index 95d4848c5d2..635b4c31ee1 100644
--- a/backend/python/autogptq/requirements-intel.txt
+++ b/backend/python/autogptq/requirements-intel.txt
@@ -2,4 +2,4 @@
 intel-extension-for-pytorch
 torch
 optimum[openvino]
-setuptools==69.5.1 # https://github.com/mudler/LocalAI/issues/2406
\ No newline at end of file
+setuptools==70.3.0 # https://github.com/mudler/LocalAI/issues/2406
\ No newline at end of file
diff --git a/backend/python/autogptq/requirements.txt b/backend/python/autogptq/requirements.txt
index 7a18bfc0de7..d0909834434 100644
--- a/backend/python/autogptq/requirements.txt
+++ b/backend/python/autogptq/requirements.txt
@@ -1,6 +1,6 @@
 accelerate
 auto-gptq==0.7.1
-grpcio==1.64.0
+grpcio==1.64.1
 protobuf
 torch
 certifi
diff --git a/backend/python/bark/requirements-intel.txt b/backend/python/bark/requirements-intel.txt
index e6b4afc011c..5c4aa6a5ce6 100644
--- a/backend/python/bark/requirements-intel.txt
+++ b/backend/python/bark/requirements-intel.txt
@@ -3,4 +3,4 @@ intel-extension-for-pytorch
 torch
 torchaudio
 optimum[openvino]
-setuptools==69.5.1 # https://github.com/mudler/LocalAI/issues/2406
\ No newline at end of file
+setuptools==70.3.0 # https://github.com/mudler/LocalAI/issues/2406
\ No newline at end of file
diff --git a/backend/python/bark/requirements.txt b/backend/python/bark/requirements.txt
index 6680a8b5afe..a8e55624d0f 100644
--- a/backend/python/bark/requirements.txt
+++ b/backend/python/bark/requirements.txt
@@ -1,6 +1,6 @@
 accelerate
 bark==0.1.5
-grpcio==1.64.0
+grpcio==1.64.1
 protobuf
 certifi
 transformers
\ No newline at end of file
diff --git a/backend/python/common/template/requirements.txt b/backend/python/common/template/requirements.txt
index 4a3bd2bc8ec..59741e9c12b 100644
--- a/backend/python/common/template/requirements.txt
+++ b/backend/python/common/template/requirements.txt
@@ -1,2 +1,2 @@
-grpcio==1.64.0
+grpcio==1.64.1
 protobuf
\ No newline at end of file
diff --git a/backend/python/coqui/requirements-intel.txt b/backend/python/coqui/requirements-intel.txt
index e6b4afc011c..5c4aa6a5ce6 100644
--- a/backend/python/coqui/requirements-intel.txt
+++ b/backend/python/coqui/requirements-intel.txt
@@ -3,4 +3,4 @@ intel-extension-for-pytorch
 torch
 torchaudio
 optimum[openvino]
-setuptools==69.5.1 # https://github.com/mudler/LocalAI/issues/2406
\ No newline at end of file
+setuptools==70.3.0 # https://github.com/mudler/LocalAI/issues/2406
\ No newline at end of file
diff --git a/backend/python/coqui/requirements.txt b/backend/python/coqui/requirements.txt
index 24621f341ef..b65c98c729e 100644
--- a/backend/python/coqui/requirements.txt
+++ b/backend/python/coqui/requirements.txt
@@ -1,6 +1,6 @@
 accelerate
 TTS==0.22.0
-grpcio==1.64.0
+grpcio==1.64.1
 protobuf
 certifi
 transformers
\ No newline at end of file
diff --git a/backend/python/diffusers/requirements-intel.txt b/backend/python/diffusers/requirements-intel.txt
index 3637b3226bd..c393b11896d 100644
--- a/backend/python/diffusers/requirements-intel.txt
+++ b/backend/python/diffusers/requirements-intel.txt
@@ -3,4 +3,4 @@ intel-extension-for-pytorch
 torch
 torchvision
 optimum[openvino]
-setuptools==69.5.1 # https://github.com/mudler/LocalAI/issues/2406
\ No newline at end of file
+setuptools==70.3.0 # https://github.com/mudler/LocalAI/issues/2406
\ No newline at end of file
diff --git a/backend/python/diffusers/requirements.txt b/backend/python/diffusers/requirements.txt
index 188fb5dc025..4c763993d0f 100644
--- a/backend/python/diffusers/requirements.txt
+++ b/backend/python/diffusers/requirements.txt
@@ -1,7 +1,7 @@
 accelerate
 compel
 diffusers
-grpcio==1.64.0
+grpcio==1.64.1
 opencv-python
 pillow
 protobuf
diff --git a/backend/python/exllama/requirements.txt b/backend/python/exllama/requirements.txt
index 7a1d5464cdd..8bb85447424 100644
--- a/backend/python/exllama/requirements.txt
+++ b/backend/python/exllama/requirements.txt
@@ -1,4 +1,4 @@
-grpcio==1.64.0
+grpcio==1.64.1
 protobuf
 torch
 transformers
diff --git a/backend/python/exllama2/requirements.txt b/backend/python/exllama2/requirements.txt
index e9aa977f282..4baead69111 100644
--- a/backend/python/exllama2/requirements.txt
+++ b/backend/python/exllama2/requirements.txt
@@ -1,5 +1,5 @@
 accelerate
-grpcio==1.64.0
+grpcio==1.64.1
 protobuf
 certifi
 torch
diff --git a/backend/python/mamba/requirements-install.txt b/backend/python/mamba/requirements-install.txt
index e937855dc4c..2fc9a07cda7 100644
--- a/backend/python/mamba/requirements-install.txt
+++ b/backend/python/mamba/requirements-install.txt
@@ -4,4 +4,4 @@
 packaging
 setuptools
 wheel
-torch==2.2.0
\ No newline at end of file
+torch==2.3.1
\ No newline at end of file
diff --git a/backend/python/mamba/requirements.txt b/backend/python/mamba/requirements.txt
index 8b08951279b..4b704f861c4 100644
--- a/backend/python/mamba/requirements.txt
+++ b/backend/python/mamba/requirements.txt
@@ -1,6 +1,6 @@
-causal-conv1d==1.2.0.post2
-mamba-ssm==1.2.0.post1
-grpcio==1.64.0
+causal-conv1d==1.4.0
+mamba-ssm==2.2.2
+grpcio==1.64.1
 protobuf
 certifi
 transformers
\ No newline at end of file
diff --git a/backend/python/openvoice/requirements-intel.txt b/backend/python/openvoice/requirements-intel.txt
index 83700d02e38..e971e044291 100644
--- a/backend/python/openvoice/requirements-intel.txt
+++ b/backend/python/openvoice/requirements-intel.txt
@@ -4,13 +4,13 @@ torch
 optimum[openvino]
 grpcio==1.64.1
 protobuf
-librosa==0.9.1
-faster-whisper==0.9.0
+librosa==0.10.2.post1
+faster-whisper==1.0.3
 pydub==0.25.1
 wavmark==0.0.3
-numpy==1.26.4
+numpy==2.0.0
 eng_to_ipa==0.0.2
-inflect==7.0.0
+inflect==7.3.1
 unidecode==1.3.7
 whisper-timestamped==1.15.4
 openai
@@ -18,6 +18,6 @@ python-dotenv
 pypinyin==0.50.0
 cn2an==0.5.22
 jieba==0.42.1
-gradio==4.36.1
+gradio==4.38.1
 langid==1.1.6
 git+https://github.com/myshell-ai/MeloTTS.git
diff --git a/backend/python/parler-tts/requirements-intel.txt b/backend/python/parler-tts/requirements-intel.txt
index e6b4afc011c..5c4aa6a5ce6 100644
--- a/backend/python/parler-tts/requirements-intel.txt
+++ b/backend/python/parler-tts/requirements-intel.txt
@@ -3,4 +3,4 @@ intel-extension-for-pytorch
 torch
 torchaudio
 optimum[openvino]
-setuptools==69.5.1 # https://github.com/mudler/LocalAI/issues/2406
\ No newline at end of file
+setuptools==70.3.0 # https://github.com/mudler/LocalAI/issues/2406
\ No newline at end of file
diff --git a/backend/python/parler-tts/requirements.txt b/backend/python/parler-tts/requirements.txt
index ba30594fa4d..c9400f76d6a 100644
--- a/backend/python/parler-tts/requirements.txt
+++ b/backend/python/parler-tts/requirements.txt
@@ -1,5 +1,5 @@
 accelerate
-grpcio==1.64.0
+grpcio==1.64.1
 protobuf
 torch
 git+https://github.com/huggingface/parler-tts.git@10016fb0300c0dc31a0fb70e26f3affee7b62f16
diff --git a/backend/python/petals/requirements-intel.txt b/backend/python/petals/requirements-intel.txt
index 95d4848c5d2..635b4c31ee1 100644
--- a/backend/python/petals/requirements-intel.txt
+++ b/backend/python/petals/requirements-intel.txt
@@ -2,4 +2,4 @@
 intel-extension-for-pytorch
 torch
 optimum[openvino]
-setuptools==69.5.1 # https://github.com/mudler/LocalAI/issues/2406
\ No newline at end of file
+setuptools==70.3.0 # https://github.com/mudler/LocalAI/issues/2406
\ No newline at end of file
diff --git a/backend/python/rerankers/requirements-intel.txt b/backend/python/rerankers/requirements-intel.txt
index 95d4848c5d2..635b4c31ee1 100644
--- a/backend/python/rerankers/requirements-intel.txt
+++ b/backend/python/rerankers/requirements-intel.txt
@@ -2,4 +2,4 @@
 intel-extension-for-pytorch
 torch
 optimum[openvino]
-setuptools==69.5.1 # https://github.com/mudler/LocalAI/issues/2406
\ No newline at end of file
+setuptools==70.3.0 # https://github.com/mudler/LocalAI/issues/2406
\ No newline at end of file
diff --git a/backend/python/rerankers/requirements.txt b/backend/python/rerankers/requirements.txt
index db861321f87..3678f483a80 100644
--- a/backend/python/rerankers/requirements.txt
+++ b/backend/python/rerankers/requirements.txt
@@ -1,6 +1,6 @@
 accelerate
 rerankers[transformers]
-grpcio==1.64.0
+grpcio==1.64.1
 protobuf
 certifi
 transformers
\ No newline at end of file
diff --git a/backend/python/sentencetransformers/requirements-intel.txt b/backend/python/sentencetransformers/requirements-intel.txt
index 95d4848c5d2..635b4c31ee1 100644
--- a/backend/python/sentencetransformers/requirements-intel.txt
+++ b/backend/python/sentencetransformers/requirements-intel.txt
@@ -2,4 +2,4 @@
 intel-extension-for-pytorch
 torch
 optimum[openvino]
-setuptools==69.5.1 # https://github.com/mudler/LocalAI/issues/2406
\ No newline at end of file
+setuptools==70.3.0 # https://github.com/mudler/LocalAI/issues/2406
\ No newline at end of file
diff --git a/backend/python/sentencetransformers/requirements.txt b/backend/python/sentencetransformers/requirements.txt
index d3f4e1f3d5f..9f0d0e638e3 100644
--- a/backend/python/sentencetransformers/requirements.txt
+++ b/backend/python/sentencetransformers/requirements.txt
@@ -1,6 +1,6 @@
 accelerate
-sentence-transformers==2.5.1
+sentence-transformers==3.0.1
 transformers
-grpcio==1.64.0
+grpcio==1.64.1
 protobuf
 certifi
\ No newline at end of file
diff --git a/backend/python/transformers-musicgen/requirements-intel.txt b/backend/python/transformers-musicgen/requirements-intel.txt
index 95d4848c5d2..635b4c31ee1 100644
--- a/backend/python/transformers-musicgen/requirements-intel.txt
+++ b/backend/python/transformers-musicgen/requirements-intel.txt
@@ -2,4 +2,4 @@
 intel-extension-for-pytorch
 torch
 optimum[openvino]
-setuptools==69.5.1 # https://github.com/mudler/LocalAI/issues/2406
\ No newline at end of file
+setuptools==70.3.0 # https://github.com/mudler/LocalAI/issues/2406
\ No newline at end of file
diff --git a/backend/python/transformers-musicgen/requirements.txt b/backend/python/transformers-musicgen/requirements.txt
index 06588c5c3a4..25f8f6a283b 100644
--- a/backend/python/transformers-musicgen/requirements.txt
+++ b/backend/python/transformers-musicgen/requirements.txt
@@ -1,7 +1,7 @@
 accelerate
 transformers
-grpcio==1.64.0
+grpcio==1.64.1
 protobuf
 torch
-scipy==1.13.0
+scipy==1.14.0
 certifi
\ No newline at end of file
diff --git a/backend/python/transformers/requirements-intel.txt b/backend/python/transformers/requirements-intel.txt
index 95d4848c5d2..635b4c31ee1 100644
--- a/backend/python/transformers/requirements-intel.txt
+++ b/backend/python/transformers/requirements-intel.txt
@@ -2,4 +2,4 @@
 intel-extension-for-pytorch
 torch
 optimum[openvino]
-setuptools==69.5.1 # https://github.com/mudler/LocalAI/issues/2406
\ No newline at end of file
+setuptools==70.3.0 # https://github.com/mudler/LocalAI/issues/2406
\ No newline at end of file
diff --git a/backend/python/transformers/requirements.txt b/backend/python/transformers/requirements.txt
index 494a53fc9ce..a4db011aca4 100644
--- a/backend/python/transformers/requirements.txt
+++ b/backend/python/transformers/requirements.txt
@@ -1,9 +1,9 @@
 accelerate
 transformers
-grpcio==1.64.0
+grpcio==1.64.1
 protobuf
 torch
 certifi
 intel-extension-for-transformers
 bitsandbytes
-setuptools==69.5.1 # https://github.com/mudler/LocalAI/issues/2406
+setuptools==70.3.0 # https://github.com/mudler/LocalAI/issues/2406
diff --git a/backend/python/vall-e-x/requirements-intel.txt b/backend/python/vall-e-x/requirements-intel.txt
index e6b4afc011c..5c4aa6a5ce6 100644
--- a/backend/python/vall-e-x/requirements-intel.txt
+++ b/backend/python/vall-e-x/requirements-intel.txt
@@ -3,4 +3,4 @@ intel-extension-for-pytorch
 torch
 torchaudio
 optimum[openvino]
-setuptools==69.5.1 # https://github.com/mudler/LocalAI/issues/2406
\ No newline at end of file
+setuptools==70.3.0 # https://github.com/mudler/LocalAI/issues/2406
\ No newline at end of file
diff --git a/backend/python/vall-e-x/requirements.txt b/backend/python/vall-e-x/requirements.txt
index a2a720f20f0..460a0cadb62 100644
--- a/backend/python/vall-e-x/requirements.txt
+++ b/backend/python/vall-e-x/requirements.txt
@@ -1,4 +1,4 @@
 accelerate
-grpcio==1.64.0
+grpcio==1.64.1
 protobuf
 certifi
\ No newline at end of file
diff --git a/backend/python/vllm/requirements-intel.txt b/backend/python/vllm/requirements-intel.txt
index 95d4848c5d2..635b4c31ee1 100644
--- a/backend/python/vllm/requirements-intel.txt
+++ b/backend/python/vllm/requirements-intel.txt
@@ -2,4 +2,4 @@
 intel-extension-for-pytorch
 torch
 optimum[openvino]
-setuptools==69.5.1 # https://github.com/mudler/LocalAI/issues/2406
\ No newline at end of file
+setuptools==70.3.0 # https://github.com/mudler/LocalAI/issues/2406
\ No newline at end of file
diff --git a/backend/python/vllm/requirements.txt b/backend/python/vllm/requirements.txt
index 0da43c3a7d9..aa61da09e4e 100644
--- a/backend/python/vllm/requirements.txt
+++ b/backend/python/vllm/requirements.txt
@@ -1,6 +1,6 @@
 accelerate
 vllm
-grpcio==1.64.0
+grpcio==1.64.1
 protobuf
 certifi
 transformers
diff --git a/core/config/guesser.go b/core/config/guesser.go
index 7cc3e99b95f..6c6ef430299 100644
--- a/core/config/guesser.go
+++ b/core/config/guesser.go
@@ -20,6 +20,7 @@ const (
 	ChatML
 	Mistral03
 	Gemma
+	DeepSeek2
 )
 
 type settingsConfig struct {
@@ -37,6 +38,17 @@ var defaultsSettings map[familyType]settingsConfig = map[familyType]settingsConf
 			Completion:  "{{.Input}}",
 		},
 	},
+	DeepSeek2: {
+		StopWords: []string{"<｜end▁of▁sentence｜>"},
+		TemplateConfig: TemplateConfig{
+			ChatMessage: `{{if eq .RoleName "user" -}}User: {{.Content }}
+{{ end -}}
+{{if eq .RoleName "assistant" -}}Assistant: {{.Content}}<｜end▁of▁sentence｜>{{end}}
+{{if eq .RoleName "system" -}}{{.Content}}
+{{end -}}`,
+			Chat: "{{.Input -}}\nAssistant: ",
+		},
+	},
 	LLaMa3: {
 		StopWords: []string{"<|eot_id|>"},
 		TemplateConfig: TemplateConfig{
@@ -208,8 +220,11 @@ func identifyFamily(f *gguf.GGUFFile) familyType {
 	qwen2 := arch == "qwen2"
 	phi3 := arch == "phi-3"
 	gemma := strings.HasPrefix(f.Model().Name, "gemma")
+	deepseek2 := arch == "deepseek2"
 
 	switch {
+	case deepseek2:
+		return DeepSeek2
 	case gemma:
 		return Gemma
 	case llama3:
diff --git a/docs/themes/hugo-theme-relearn b/docs/themes/hugo-theme-relearn
index c25bc2a27ab..1b2e1395121 160000
--- a/docs/themes/hugo-theme-relearn
+++ b/docs/themes/hugo-theme-relearn
@@ -1 +1 @@
-Subproject commit c25bc2a27ab46649393ef7b310e14fff1311116d
+Subproject commit 1b2e139512106f8074ac7d4a884135d159720cc4
diff --git a/examples/chainlit/requirements.txt b/examples/chainlit/requirements.txt
index 95191f623f7..116b7b61f07 100644
--- a/examples/chainlit/requirements.txt
+++ b/examples/chainlit/requirements.txt
@@ -1,6 +1,6 @@
-llama_index==0.9.48
+llama_index==0.10.55
 requests==2.32.3
-weaviate_client==4.6.4
+weaviate_client==4.6.5
 transformers
 torch
 chainlit
diff --git a/examples/functions/requirements.txt b/examples/functions/requirements.txt
index 6c00efd4b76..d43c751795a 100644
--- a/examples/functions/requirements.txt
+++ b/examples/functions/requirements.txt
@@ -1,2 +1,2 @@
-langchain==0.2.3
-openai==1.33.0
+langchain==0.2.7
+openai==1.35.13
diff --git a/examples/k8sgpt/broken-pod.yaml b/examples/k8sgpt/broken-pod.yaml
index 8b7e8e0f588..9d5289def06 100644
--- a/examples/k8sgpt/broken-pod.yaml
+++ b/examples/k8sgpt/broken-pod.yaml
@@ -5,7 +5,7 @@ metadata:
 spec:
   containers:
     - name: broken-pod
-      image: nginx:1.a.b.c
+      image: nginx:1.27.0
       livenessProbe:
         httpGet:
           path: /
diff --git a/examples/langchain-chroma/requirements.txt b/examples/langchain-chroma/requirements.txt
index 9d28fc3b152..dcaeecc4b9e 100644
--- a/examples/langchain-chroma/requirements.txt
+++ b/examples/langchain-chroma/requirements.txt
@@ -1,4 +1,4 @@
-langchain==0.2.3
-openai==1.33.0
-chromadb==0.5.0
-llama-index==0.10.43
\ No newline at end of file
+langchain==0.2.7
+openai==1.35.13
+chromadb==0.5.4
+llama-index==0.10.55
\ No newline at end of file
diff --git a/examples/langchain/langchainpy-localai-example/requirements.txt b/examples/langchain/langchainpy-localai-example/requirements.txt
index 8d6da459a4d..9dfce8466e2 100644
--- a/examples/langchain/langchainpy-localai-example/requirements.txt
+++ b/examples/langchain/langchainpy-localai-example/requirements.txt
@@ -2,7 +2,7 @@ aiohttp==3.9.5
 aiosignal==1.3.1
 async-timeout==4.0.3
 attrs==23.2.0
-certifi==2024.6.2
+certifi==2024.7.4
 charset-normalizer==3.3.2
 colorama==0.4.6
 dataclasses-json==0.6.7
@@ -10,8 +10,8 @@ debugpy==1.8.1
 frozenlist==1.4.1
 greenlet==3.0.3
 idna==3.7
-langchain==0.2.3
-langchain-community==0.2.4
+langchain==0.2.7
+langchain-community==0.2.5
 marshmallow==3.21.3
 marshmallow-enum==1.5.1
 multidict==6.0.5
@@ -21,13 +21,13 @@ numpy==1.26.4
 openai==1.33.0
 openapi-schema-pydantic==1.2.4
 packaging>=23.2
-pydantic==2.7.3
+pydantic==2.8.2
 PyYAML==6.0.1
 requests==2.32.3
 SQLAlchemy==2.0.30
-tenacity==8.3.0
+tenacity==8.5.0
 tqdm==4.66.4
 typing-inspect==0.9.0
 typing_extensions==4.12.2
-urllib3==2.2.1
+urllib3==2.2.2
 yarl==1.9.4
diff --git a/examples/streamlit-bot/requirements.txt b/examples/streamlit-bot/requirements.txt
index 1fcd5093281..ed2a59809ff 100644
--- a/examples/streamlit-bot/requirements.txt
+++ b/examples/streamlit-bot/requirements.txt
@@ -1,2 +1,2 @@
-streamlit==1.30.0
+streamlit==1.36.0
 requests
\ No newline at end of file
diff --git a/gallery/deepseek.yaml b/gallery/deepseek.yaml
new file mode 100644
index 00000000000..fa8870a1d54
--- /dev/null
+++ b/gallery/deepseek.yaml
@@ -0,0 +1,20 @@
+---
+name: "deepseek"
+
+config_file: |
+  mmap: true
+  context_size: 8192
+  template:
+    chat_message: |-
+      {{if eq .RoleName "user" -}}User: {{.Content }}
+      {{ end -}}
+      {{if eq .RoleName "assistant" -}}Assistant: {{.Content}}<｜end▁of▁sentence｜>{{end}}
+      {{if eq .RoleName "system" -}}{{.Content}}
+      {{end -}}
+    chat: |
+      {{.Input -}}
+      Assistant: # Space is preserved for templating reasons, but line does not end with one for the linter.
+    completion: |
+      {{.Input}}
+  stopwords:
+  - '<｜end▁of▁sentence｜>'
diff --git a/gallery/index.yaml b/gallery/index.yaml
index fc47e6ce814..bd01042cd3a 100644
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@@ -1,4 +1,29 @@
 ---
+## Deepseek
+- &deepseek
+  url: "github:mudler/LocalAI/gallery/deepseek.yaml@master"
+  name: "deepseek-coder-v2-lite-instruct"
+  icon: "https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/logo.svg?raw=true"
+  license: deepseek
+  description: |
+    DeepSeek-Coder-V2, an open-source Mixture-of-Experts (MoE) code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks. Specifically, DeepSeek-Coder-V2 is further pre-trained from DeepSeek-Coder-V2-Base with 6 trillion tokens sourced from a high-quality and multi-source corpus. Through this continued pre-training, DeepSeek-Coder-V2 substantially enhances the coding and mathematical reasoning capabilities of DeepSeek-Coder-V2-Base, while maintaining comparable performance in general language tasks. Compared to DeepSeek-Coder, DeepSeek-Coder-V2 demonstrates significant advancements in various aspects of code-related tasks, as well as reasoning and general capabilities. Additionally, DeepSeek-Coder-V2 expands its support for programming languages from 86 to 338, while extending the context length from 16K to 128K.
+    In standard benchmark evaluations, DeepSeek-Coder-V2 achieves superior performance compared to closed-source models such as GPT4-Turbo, Claude 3 Opus, and Gemini 1.5 Pro in coding and math benchmarks. The list of supported programming languages can be found in the paper.
+  urls:
+    - https://github.com/deepseek-ai/DeepSeek-Coder-V2/tree/main
+    - https://huggingface.co/LoneStriker/DeepSeek-Coder-V2-Lite-Instruct-GGUF
+  tags:
+    - llm
+    - gguf
+    - gpu
+    - deepseek
+    - cpu
+  overrides:
+    parameters:
+      model: DeepSeek-Coder-V2-Lite-Instruct-Q4_K_M.gguf
+  files:
+    - filename: DeepSeek-Coder-V2-Lite-Instruct-Q4_K_M.gguf
+      sha256: 50ec78036433265965ed1afd0667c00c71c12aa70bcf383be462cb8e159db6c0
+      uri: huggingface://LoneStriker/DeepSeek-Coder-V2-Lite-Instruct-GGUF/DeepSeek-Coder-V2-Lite-Instruct-Q4_K_M.gguf
 ## Start QWEN2
 - &qwen2
   url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
@@ -514,6 +539,25 @@
     - filename: Smegmma-Deluxe-9B-v1-Q4_K_M.gguf
       uri: huggingface://bartowski/Smegmma-Deluxe-9B-v1-GGUF/Smegmma-Deluxe-9B-v1-Q4_K_M.gguf
       sha256: 732ecb253ea0115453438fc1f4e3e31507719ddcf81890a86ad1d734beefdb6f
+- !!merge <<: *gemma
+  name: "tiger-gemma-9b-v1-i1"
+  icon: https://cdn-uploads.huggingface.co/production/uploads/65f2fd1c25b848bd061b5c2e/A97OlLKeT4XOnv4IG1b6m.png
+  urls:
+    - https://huggingface.co/TheDrummer/Tiger-Gemma-9B-v1
+    - https://huggingface.co/mradermacher/Tiger-Gemma-9B-v1-i1-GGUF
+  description: |
+    Tiger Gemma 9B v1
+
+    Decensored Gemma 9B. No refusals so far. No apparent brain damage.
+
+    In memory of Tiger
+  overrides:
+    parameters:
+      model: Tiger-Gemma-9B-v1.i1-Q4_K_M.gguf
+  files:
+    - filename: Tiger-Gemma-9B-v1.i1-Q4_K_M.gguf
+      sha256: ef10accfee8023b31def5425bf591bf1f0203090f3dd851cd3f37bb235324383
+      uri: huggingface://mradermacher/Tiger-Gemma-9B-v1-i1-GGUF/Tiger-Gemma-9B-v1.i1-Q4_K_M.gguf
 - &llama3
   url: "github:mudler/LocalAI/gallery/llama3-instruct.yaml@master"
   icon: https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/aJJxKus1wP5N-euvHEUq7.png
@@ -2708,6 +2752,71 @@
     - filename: Llama-3-Patronus-Lynx-70B-Instruct.Q4_K_M.gguf
       sha256: 95a02b71baff287bd84188fc1babcf9dfae25c315e2613391e694cf944f1e5b3
       uri: huggingface://mradermacher/Llama-3-Patronus-Lynx-70B-Instruct-GGUF/Llama-3-Patronus-Lynx-70B-Instruct.Q4_K_M.gguf
+- !!merge <<: *llama3
+  name: "llamax3-8b-alpaca"
+  urls:
+    - https://huggingface.co/LLaMAX/LLaMAX3-8B-Alpaca
+    - https://huggingface.co/mradermacher/LLaMAX3-8B-Alpaca-GGUF
+  description: |
+    LLaMAX is a language model with powerful multilingual capabilities without loss instruction-following capabilities.
+
+    We collected extensive training sets in 102 languages for continued pre-training of Llama2 and leveraged the English instruction fine-tuning dataset, Alpaca, to fine-tune its instruction-following capabilities.
+
+    LLaMAX supports translation between more than 100 languages, surpassing the performance of similarly scaled LLMs.
+
+    Supported Languages
+    Akrikaans (af), Amharic (am), Arabic (ar), Armenian (hy), Assamese (as), Asturian (ast), Azerbaijani (az), Belarusian (be), Bengali (bn), Bosnian (bs), Bulgarian (bg), Burmese (my), Catalan (ca), Cebuano (ceb), Chinese Simpl (zho), Chinese Trad (zho), Croatian (hr), Czech (cs), Danish (da), Dutch (nl), English (en), Estonian (et), Filipino (tl), Finnish (fi), French (fr), Fulah (ff), Galician (gl), Ganda (lg), Georgian (ka), German (de), Greek (el), Gujarati (gu), Hausa (ha), Hebrew (he), Hindi (hi), Hungarian (hu), Icelandic (is), Igbo (ig), Indonesian (id), Irish (ga), Italian (it), Japanese (ja), Javanese (jv), Kabuverdianu (kea), Kamba (kam), Kannada (kn), Kazakh (kk), Khmer (km), Korean (ko), Kyrgyz (ky), Lao (lo), Latvian (lv), Lingala (ln), Lithuanian (lt), Luo (luo), Luxembourgish (lb), Macedonian (mk), Malay (ms), Malayalam (ml), Maltese (mt), Maori (mi), Marathi (mr), Mongolian (mn), Nepali (ne), Northern Sotho (ns), Norwegian (no), Nyanja (ny), Occitan (oc), Oriya (or), Oromo (om), Pashto (ps), Persian (fa), Polish (pl), Portuguese (pt), Punjabi (pa), Romanian (ro), Russian (ru), Serbian (sr), Shona (sn), Sindhi (sd), Slovak (sk), Slovenian (sl), Somali (so), Sorani Kurdish (ku), Spanish (es), Swahili (sw), Swedish (sv), Tajik (tg), Tamil (ta), Telugu (te), Thai (th), Turkish (tr), Ukrainian (uk), Umbundu (umb), Urdu (ur), Uzbek (uz), Vietnamese (vi), Welsh (cy), Wolof (wo), Xhosa (xh), Yoruba (yo), Zulu (zu)
+  overrides:
+    parameters:
+      model: LLaMAX3-8B-Alpaca.Q4_K_M.gguf
+  files:
+    - filename: LLaMAX3-8B-Alpaca.Q4_K_M.gguf
+      sha256: 4652209c55d4260634b2195989279f945a072d8574872789a40d1f9b86eb255b
+      uri: huggingface://mradermacher/LLaMAX3-8B-Alpaca-GGUF/LLaMAX3-8B-Alpaca.Q4_K_M.gguf
+- !!merge <<: *llama3
+  name: "llamax3-8b"
+  urls:
+    - https://huggingface.co/LLaMAX/LLaMAX3-8B
+    - https://huggingface.co/mradermacher/LLaMAX3-8B-GGUF
+  description: |
+    LLaMAX is a language model with powerful multilingual capabilities without loss instruction-following capabilities.
+
+    We collected extensive training sets in 102 languages for continued pre-training of Llama2 and leveraged the English instruction fine-tuning dataset, Alpaca, to fine-tune its instruction-following capabilities.
+
+    LLaMAX supports translation between more than 100 languages, surpassing the performance of similarly scaled LLMs.
+
+    Supported Languages
+    Akrikaans (af), Amharic (am), Arabic (ar), Armenian (hy), Assamese (as), Asturian (ast), Azerbaijani (az), Belarusian (be), Bengali (bn), Bosnian (bs), Bulgarian (bg), Burmese (my), Catalan (ca), Cebuano (ceb), Chinese Simpl (zho), Chinese Trad (zho), Croatian (hr), Czech (cs), Danish (da), Dutch (nl), English (en), Estonian (et), Filipino (tl), Finnish (fi), French (fr), Fulah (ff), Galician (gl), Ganda (lg), Georgian (ka), German (de), Greek (el), Gujarati (gu), Hausa (ha), Hebrew (he), Hindi (hi), Hungarian (hu), Icelandic (is), Igbo (ig), Indonesian (id), Irish (ga), Italian (it), Japanese (ja), Javanese (jv), Kabuverdianu (kea), Kamba (kam), Kannada (kn), Kazakh (kk), Khmer (km), Korean (ko), Kyrgyz (ky), Lao (lo), Latvian (lv), Lingala (ln), Lithuanian (lt), Luo (luo), Luxembourgish (lb), Macedonian (mk), Malay (ms), Malayalam (ml), Maltese (mt), Maori (mi), Marathi (mr), Mongolian (mn), Nepali (ne), Northern Sotho (ns), Norwegian (no), Nyanja (ny), Occitan (oc), Oriya (or), Oromo (om), Pashto (ps), Persian (fa), Polish (pl), Portuguese (pt), Punjabi (pa), Romanian (ro), Russian (ru), Serbian (sr), Shona (sn), Sindhi (sd), Slovak (sk), Slovenian (sl), Somali (so), Sorani Kurdish (ku), Spanish (es), Swahili (sw), Swedish (sv), Tajik (tg), Tamil (ta), Telugu (te), Thai (th), Turkish (tr), Ukrainian (uk), Umbundu (umb), Urdu (ur), Uzbek (uz), Vietnamese (vi), Welsh (cy), Wolof (wo), Xhosa (xh), Yoruba (yo), Zulu (zu)
+  overrides:
+    parameters:
+      model: LLaMAX3-8B.Q4_K_M.gguf
+  files:
+    - filename: LLaMAX3-8B.Q4_K_M.gguf
+      sha256: 862fb2be5d74b171f4294f862f43e7cb6e6dbecce29a9f9167da4f1db230daac
+      uri: huggingface://mradermacher/LLaMAX3-8B-GGUF/LLaMAX3-8B.Q4_K_M.gguf
+- !!merge <<: *llama3
+  name: "arliai-llama-3-8b-dolfin-v0.5"
+  urls:
+    - https://huggingface.co/OwenArli/ArliAI-Llama-3-8B-Dolfin-v0.5
+    - https://huggingface.co/QuantFactory/ArliAI-Llama-3-8B-Dolfin-v0.5-GGUF
+  description: |
+    Based on Meta-Llama-3-8b-Instruct, and is governed by Meta Llama 3 License agreement: https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct
+
+    This is a fine tune using an improved Dolphin and WizardLM dataset intended to make the model follow instructions better and refuse less.
+
+    OpenLLM Benchmark:
+
+    Training:
+
+        2048 sequence length since the dataset has an average length of under 1000 tokens, while the base model is 8192 sequence length. From testing it still performs the same 8192 context just fine.
+        Training duration is around 2 days on 2xRTX 3090, using 4-bit loading and Qlora 64-rank 128-alpha resulting in ~2% trainable weights.
+  overrides:
+    parameters:
+      model: ArliAI-Llama-3-8B-Dolfin-v0.5.Q4_K_M.gguf
+  files:
+    - filename: ArliAI-Llama-3-8B-Dolfin-v0.5.Q4_K_M.gguf
+      sha256: 71fef02915c606b438ccff2cae6b7760bbb54a558d5f2d39c2421d97b6682fea
+      uri: huggingface://QuantFactory/ArliAI-Llama-3-8B-Dolfin-v0.5-GGUF/ArliAI-Llama-3-8B-Dolfin-v0.5.Q4_K_M.gguf
 - &chatml
   ### ChatML
   url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
diff --git a/scripts/latest_hf.py b/scripts/latest_hf.py
index 792a9639af9..b971a6bdaf6 100644
--- a/scripts/latest_hf.py
+++ b/scripts/latest_hf.py
@@ -12,7 +12,7 @@
 
 def get_latest_model():
     search_term = "GGUF"
-    if sys.argv[1]:
+    if len(sys.argv) > 2 and sys.argv[1]:
         search_term = sys.argv[1]
     url = "https://huggingface.co/api/models"
     params = {"sort": "lastModified", "direction": -1, "limit": 30, "search": search_term}