diff --git a/.github/workflows/build-portable-release-cuda.yml b/.github/workflows/build-portable-release-cuda.yml
index b304dcd6..a10e8ec4 100644
--- a/.github/workflows/build-portable-release-cuda.yml
+++ b/.github/workflows/build-portable-release-cuda.yml
@@ -59,7 +59,6 @@ jobs:
           $matrix = @{
               'os' = @('ubuntu-22.04', 'windows-2022')
               'pyver' = @("3.13")
-              'avx' = @("AVX2")
               'cuda' = @("12.4")
           }
 
@@ -75,7 +74,7 @@ jobs:
           Write-Output ('matrix=' + $matrixOut) >> $env:GITHUB_OUTPUT
 
   build_wheels:
-    name: ${{ matrix.os }} ${{ matrix.pyver }} CPU ${{ matrix.avx }} CUDA ${{ matrix.cuda }}
+    name: ${{ matrix.os }} ${{ matrix.pyver }} CUDA ${{ matrix.cuda }}
     needs: define_matrix
     runs-on: ${{ matrix.os }}
     strategy:
@@ -84,7 +83,6 @@ jobs:
       run:
         shell: pwsh
     env:
-      AVXVER: ${{ matrix.avx }}
       PCKGVER: ${{ inputs.version }}
 
     steps:
@@ -113,7 +111,6 @@ jobs:
 
             # Define common variables
             CUDA_VERSION="${{ matrix.cuda }}"
-            AVX_SUPPORT="${{ matrix.avx }}"
             VERSION="${{ inputs.version }}"
 
             # 1. Set platform-specific variables
@@ -138,16 +135,9 @@ jobs:
             tar -xzf python-build.tar.gz
             mv python "text-generation-webui-${VERSION_CLEAN}/portable_env"
 
-            # 3. Prepare requirements file based on AVX and CUDA
-            if [[ "$AVX_SUPPORT" == "AVX2" ]]; then
-                BASE_REQ_FILE="requirements/portable/requirements.txt"
-            else
-                BASE_REQ_FILE="requirements/portable/requirements_noavx2.txt"
-            fi
-
-            # Create CUDA-specific requirements file if needed
+            # 3. Prepare requirements file
             cd "text-generation-webui-${VERSION_CLEAN}"
-            REQ_FILE="$BASE_REQ_FILE"
+            REQ_FILE="requirements/portable/requirements.txt"
 
             # 4. Install packages
             echo "Installing Python packages from $REQ_FILE..."
diff --git a/.github/workflows/build-portable-release-rocm.yml b/.github/workflows/build-portable-release-rocm.yml
index 0a150806..5b43b2d3 100644
--- a/.github/workflows/build-portable-release-rocm.yml
+++ b/.github/workflows/build-portable-release-rocm.yml
@@ -57,9 +57,8 @@ jobs:
         id: set-matrix
         run: |
           $matrix = @{
-              'os' = @('ubuntu-22.04')
+              'os' = @('ubuntu-22.04', 'windows-2022')
               'pyver' = @("3.13")
-              'avx' = @("AVX2")
           }
 
           if ($env:CONFIGIN -ne 'Default') {$env:CONFIGIN.split(';').foreach({$matrix[$_.split(':')[0]] = $_.split(':')[1].split(',')})}
@@ -74,7 +73,7 @@ jobs:
           Write-Output ('matrix=' + $matrixOut) >> $env:GITHUB_OUTPUT
 
   build_wheels:
-    name: ${{ matrix.os }} ${{ matrix.pyver }} CPU ${{ matrix.avx }}
+    name: ${{ matrix.os }} ${{ matrix.pyver }}
     needs: define_matrix
     runs-on: ${{ matrix.os }}
     strategy:
@@ -83,7 +82,6 @@ jobs:
       run:
         shell: pwsh
     env:
-      AVXVER: ${{ matrix.avx }}
       PCKGVER: ${{ inputs.version }}
 
     steps:
@@ -111,15 +109,22 @@ jobs:
             find extensions/ -mindepth 1 -maxdepth 1 -type d | grep -v -E "$(printf '%s|' "${allowed[@]}" | sed 's/|$//')" | xargs rm -rf
 
             # Define common variables
-            AVX_SUPPORT="${{ matrix.avx }}"
             VERSION="${{ inputs.version }}"
 
-            # 1. Set platform-specific variables (Linux only for ROCm)
-            PLATFORM="linux"
-            PYTHON_URL="https://github.com/astral-sh/python-build-standalone/releases/download/20260303/cpython-3.13.12+20260303-x86_64-unknown-linux-gnu-install_only.tar.gz"
-            PIP_PATH="portable_env/bin/python -m pip"
-            PACKAGES_PATH="portable_env/lib/python3.13/site-packages"
-            rm start_macos.sh start_windows.bat
+            # 1. Set platform-specific variables
+            if [[ "$RUNNER_OS" == "Windows" ]]; then
+                PLATFORM="windows"
+                PYTHON_URL="https://github.com/astral-sh/python-build-standalone/releases/download/20260303/cpython-3.13.12+20260303-x86_64-pc-windows-msvc-install_only.tar.gz"
+                PIP_PATH="portable_env/python.exe -m pip"
+                PACKAGES_PATH="portable_env/Lib/site-packages"
+                rm start_linux.sh start_macos.sh
+            else
+                PLATFORM="linux"
+                PYTHON_URL="https://github.com/astral-sh/python-build-standalone/releases/download/20260303/cpython-3.13.12+20260303-x86_64-unknown-linux-gnu-install_only.tar.gz"
+                PIP_PATH="portable_env/bin/python -m pip"
+                PACKAGES_PATH="portable_env/lib/python3.13/site-packages"
+                rm start_macos.sh start_windows.bat
+            fi
 
             # 2. Download and extract Python
             cd ..
@@ -128,13 +133,8 @@ jobs:
             tar -xzf python-build.tar.gz
             mv python "text-generation-webui-${VERSION_CLEAN}/portable_env"
 
-            # 3. Prepare requirements file based on AVX
-            if [[ "$AVX_SUPPORT" == "AVX2" ]]; then
-                BASE_REQ_FILE="requirements/portable/requirements_amd.txt"
-            else
-                BASE_REQ_FILE="requirements/portable/requirements_amd_noavx2.txt"
-            fi
-            REQ_FILE="$BASE_REQ_FILE"
+            # 3. Prepare requirements file
+            REQ_FILE="requirements/portable/requirements_amd.txt"
 
             cd "text-generation-webui-${VERSION_CLEAN}"
 
@@ -150,7 +150,11 @@ jobs:
             ZIP_NAME="textgen-portable-${VERSION_CLEAN}-${PLATFORM}-rocm.zip"
             echo "Creating archive: $ZIP_NAME"
 
-            zip -r "$ZIP_NAME" "text-generation-webui-${VERSION_CLEAN}"
+            if [[ "$RUNNER_OS" == "Windows" ]]; then
+                powershell -Command "Compress-Archive -Path text-generation-webui-${VERSION_CLEAN} -DestinationPath $ZIP_NAME"
+            else
+                zip -r "$ZIP_NAME" "text-generation-webui-${VERSION_CLEAN}"
+            fi
 
       - name: Upload files to a GitHub release
         id: upload-release
diff --git a/.github/workflows/build-portable-release-vulkan.yml b/.github/workflows/build-portable-release-vulkan.yml
index eda684b1..e8b75b5b 100644
--- a/.github/workflows/build-portable-release-vulkan.yml
+++ b/.github/workflows/build-portable-release-vulkan.yml
@@ -59,7 +59,6 @@ jobs:
           $matrix = @{
               'os' = @('ubuntu-22.04', 'windows-2022')
               'pyver' = @("3.13")
-              'avx' = @("AVX2")
           }
 
           if ($env:CONFIGIN -ne 'Default') {$env:CONFIGIN.split(';').foreach({$matrix[$_.split(':')[0]] = $_.split(':')[1].split(',')})}
@@ -74,7 +73,7 @@ jobs:
           Write-Output ('matrix=' + $matrixOut) >> $env:GITHUB_OUTPUT
 
   build_wheels:
-    name: ${{ matrix.os }} ${{ matrix.pyver }} CPU ${{ matrix.avx }}
+    name: ${{ matrix.os }} ${{ matrix.pyver }}
     needs: define_matrix
     runs-on: ${{ matrix.os }}
     strategy:
@@ -83,7 +82,6 @@ jobs:
       run:
         shell: pwsh
     env:
-      AVXVER: ${{ matrix.avx }}
       PCKGVER: ${{ inputs.version }}
 
     steps:
@@ -111,7 +109,6 @@ jobs:
             find extensions/ -mindepth 1 -maxdepth 1 -type d | grep -v -E "$(printf '%s|' "${allowed[@]}" | sed 's/|$//')" | xargs rm -rf
 
             # Define common variables
-            AVX_SUPPORT="${{ matrix.avx }}"
             VERSION="${{ inputs.version }}"
 
             # 1. Set platform-specific variables
@@ -136,13 +133,8 @@ jobs:
             tar -xzf python-build.tar.gz
             mv python "text-generation-webui-${VERSION_CLEAN}/portable_env"
 
-            # 3. Prepare requirements file based on AVX
-            if [[ "$AVX_SUPPORT" == "AVX2" ]]; then
-                BASE_REQ_FILE="requirements/portable/requirements_vulkan.txt"
-            else
-                BASE_REQ_FILE="requirements/portable/requirements_vulkan_noavx2.txt"
-            fi
-            REQ_FILE="$BASE_REQ_FILE"
+            # 3. Prepare requirements file
+            REQ_FILE="requirements/portable/requirements_vulkan.txt"
 
             cd "text-generation-webui-${VERSION_CLEAN}"
 
diff --git a/.github/workflows/build-portable-release.yml b/.github/workflows/build-portable-release.yml
index 1f6e4da3..a6aec751 100644
--- a/.github/workflows/build-portable-release.yml
+++ b/.github/workflows/build-portable-release.yml
@@ -59,7 +59,6 @@ jobs:
           $matrix = @{
               'os' = @('ubuntu-22.04', 'windows-2022', 'macos-14')
               'pyver' = @("3.13")
-              'avx' = @("AVX2")
           }
 
           if ($env:CONFIGIN -ne 'Default') {$env:CONFIGIN.split(';').foreach({$matrix[$_.split(':')[0]] = $_.split(':')[1].split(',')})}
@@ -74,7 +73,7 @@ jobs:
           Write-Output ('matrix=' + $matrixOut) >> $env:GITHUB_OUTPUT
 
   build_wheels:
-    name: ${{ matrix.os }} ${{ matrix.pyver }} CPU ${{ matrix.avx }}
+    name: ${{ matrix.os }} ${{ matrix.pyver }}
     needs: define_matrix
     runs-on: ${{ matrix.os }}
     strategy:
@@ -83,7 +82,6 @@ jobs:
       run:
         shell: pwsh
     env:
-      AVXVER: ${{ matrix.avx }}
       PCKGVER: ${{ inputs.version }}
 
     steps:
@@ -111,7 +109,6 @@ jobs:
             find extensions/ -mindepth 1 -maxdepth 1 -type d | grep -v -E "$(printf '%s|' "${allowed[@]}" | sed 's/|$//')" | xargs rm -rf
 
             # Define common variables
-            AVX_SUPPORT="${{ matrix.avx }}"
             VERSION="${{ inputs.version }}"
             OS_TYPE="${{ matrix.os }}"
 
@@ -151,7 +148,7 @@ jobs:
             tar -xzf python-build.tar.gz
             mv python "text-generation-webui-${VERSION_CLEAN}/portable_env"
 
-            # 3. Prepare requirements file based on platform and AVX
+            # 3. Prepare requirements file based on platform
             cd "text-generation-webui-${VERSION_CLEAN}"
 
             # Select requirements file based on platform
@@ -162,12 +159,7 @@ jobs:
                     REQ_FILE="requirements/portable/requirements_apple_silicon.txt"
                 fi
             else
-                # For Windows and Linux, check AVX support
-                if [[ "$AVX_SUPPORT" == "AVX2" ]]; then
-                    REQ_FILE="requirements/portable/requirements_cpu_only.txt"
-                else
-                    REQ_FILE="requirements/portable/requirements_cpu_only_noavx2.txt"
-                fi
+                REQ_FILE="requirements/portable/requirements_cpu_only.txt"
             fi
 
             echo "Using requirements file: $REQ_FILE"
diff --git a/README.md b/README.md
index c71fc565..2869aaec 100644
--- a/README.md
+++ b/README.md
@@ -171,16 +171,13 @@ pip install -r requirements/full/<requirements file according to table below>
 
 Requirements file to use:
 
-| GPU | CPU | requirements file to use |
-|--------|---------|---------|
-| NVIDIA | has AVX2 | `requirements.txt` |
-| NVIDIA | no AVX2 | `requirements_noavx2.txt` |
-| AMD | has AVX2 | `requirements_amd.txt` |
-| AMD | no AVX2 | `requirements_amd_noavx2.txt` |
-| CPU only | has AVX2 | `requirements_cpu_only.txt` |
-| CPU only | no AVX2 | `requirements_cpu_only_noavx2.txt` |
-| Apple | Intel | `requirements_apple_intel.txt` |
-| Apple | Apple Silicon | `requirements_apple_silicon.txt` |
+| GPU | requirements file to use |
+|--------|---------|
+| NVIDIA | `requirements.txt` |
+| AMD | `requirements_amd.txt` |
+| CPU only | `requirements_cpu_only.txt` |
+| Apple Intel | `requirements_apple_intel.txt` |
+| Apple Silicon | `requirements_apple_silicon.txt` |
 
 ### Start the web UI
 
diff --git a/one_click.py b/one_click.py
index 46e86a0c..dad9e807 100644
--- a/one_click.py
+++ b/one_click.py
@@ -65,24 +65,6 @@ def is_installed():
         return os.path.isdir(conda_env_path)
 
 
-def cpu_has_avx2():
-    try:
-        import cpuinfo
-        info = cpuinfo.get_cpu_info()
-        return 'avx2' in info['flags']
-    except:
-        return True
-
-
-def cpu_has_amx():
-    try:
-        import cpuinfo
-        info = cpuinfo.get_cpu_info()
-        return 'amx' in info['flags']
-    except:
-        return True
-
-
 def load_state():
     """Load installer state from JSON file"""
     if os.path.exists(state_file):
@@ -172,13 +154,13 @@ def get_requirements_file(gpu_choice):
     requirements_base = os.path.join("requirements", "full")
 
     if gpu_choice == "NVIDIA_CUDA128":
-        file_name = f"requirements{'_noavx2' if not cpu_has_avx2() else ''}.txt"
+        file_name = "requirements.txt"
     elif gpu_choice == "AMD":
-        file_name = f"requirements_amd{'_noavx2' if not cpu_has_avx2() else ''}.txt"
+        file_name = "requirements_amd.txt"
     elif gpu_choice == "APPLE":
         file_name = f"requirements_apple_{'intel' if is_x86_64() else 'silicon'}.txt"
     elif gpu_choice in ["INTEL", "NONE"]:
-        file_name = f"requirements_cpu_only{'_noavx2' if not cpu_has_avx2() else ''}.txt"
+        file_name = "requirements_cpu_only.txt"
     else:
         raise ValueError(f"Unknown GPU choice: {gpu_choice}")
 
@@ -327,7 +309,7 @@ def install_webui():
     elif any((is_windows(), is_linux())) and gpu_choice == "NVIDIA_CUDA128":
         print("CUDA: 12.8")
 
-    # No PyTorch for AMD on Windows (?)
+    # No PyTorch for AMD on Windows
     elif is_windows() and gpu_choice == "AMD":
         print("PyTorch setup on Windows is not implemented yet. Exiting...")
         sys.exit(1)
@@ -335,7 +317,7 @@ def install_webui():
     # Install Git and then Pytorch
     print_big_message("Installing PyTorch.")
     install_pytorch = get_pytorch_install_command(gpu_choice)
-    run_cmd(f"conda install -y ninja git && {install_pytorch} && python -m pip install py-cpuinfo==9.0.0", assert_success=True, environment=True)
+    run_cmd(f"conda install -y ninja git && {install_pytorch}", assert_success=True, environment=True)
 
     if gpu_choice == "INTEL":
         # Install oneAPI dependencies via conda
diff --git a/requirements/full/requirements.txt b/requirements/full/requirements.txt
index bed2aeb4..b948f2f5 100644
--- a/requirements/full/requirements.txt
+++ b/requirements/full/requirements.txt
@@ -42,8 +42,8 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.83.0/llama_cpp_binaries-0.83.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.83.0/llama_cpp_binaries-0.83.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/turboderp-org/exllamav3/releases/download/v0.0.22/exllamav3-0.0.22+cu128.torch2.9.0-cp313-cp313-win_amd64.whl; platform_system == "Windows" and python_version == "3.13"
 https://github.com/turboderp-org/exllamav3/releases/download/v0.0.22/exllamav3-0.0.22+cu128.torch2.9.0-cp313-cp313-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.13"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.9.0-cp313-cp313-win_amd64.whl; platform_system == "Windows" and python_version == "3.13"
diff --git a/requirements/full/requirements_amd.txt b/requirements/full/requirements_amd.txt
index 8824357c..3754b123 100644
--- a/requirements/full/requirements_amd.txt
+++ b/requirements/full/requirements_amd.txt
@@ -40,7 +40,7 @@ sse-starlette==1.6.5
 tiktoken
 
 # AMD wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+rocm6.4.4-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.83.0/llama_cpp_binaries-0.83.0+rocm6.4-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.83.0/llama_cpp_binaries-0.83.0+rocm6.4-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+rocm6.4.torch2.9.0-cp313-cp313-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.13"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
diff --git a/requirements/full/requirements_amd_noavx2.txt b/requirements/full/requirements_amd_noavx2.txt
deleted file mode 100644
index ca7f0fe9..00000000
--- a/requirements/full/requirements_amd_noavx2.txt
+++ /dev/null
@@ -1,46 +0,0 @@
-accelerate==1.12.*
-audioop-lts<1.0; python_version >= "3.13"
-colorama
-datasets
-diffusers==0.36.*
-einops
-fastapi==0.112.4
-html2text==2025.4.15
-huggingface-hub==1.5.*
-jinja2==3.1.6
-markdown
-numpy==2.2.*
-pandas
-peft==0.18.*
-Pillow>=9.5.0
-psutil
-pydantic==2.11.0
-PyPDF2==3.0.1
-python-docx==1.1.2
-pyyaml
-requests
-rich
-safetensors==0.7.*
-scipy
-sentencepiece
-tensorboard
-torchao==0.15.*
-transformers==5.2.*
-triton-windows==3.5.1.post24; platform_system == "Windows"
-tqdm
-wandb
-
-# Gradio
-gradio==4.37.*
-https://github.com/oobabooga/gradio/releases/download/custom-build/gradio_client-1.0.2+custom.1-py3-none-any.whl
-
-# API
-flask_cloudflared==0.0.14
-sse-starlette==1.6.5
-tiktoken
-
-# AMD wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+rocm6.4.torch2.9.0-cp313-cp313-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.13"
-https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
diff --git a/requirements/full/requirements_apple_intel.txt b/requirements/full/requirements_apple_intel.txt
index b9f1f1f2..eb3a3a11 100644
--- a/requirements/full/requirements_apple_intel.txt
+++ b/requirements/full/requirements_apple_intel.txt
@@ -40,5 +40,4 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.83.0/llama_cpp_binaries-0.83.0-py3-none-macosx_13_0_x86_64.whl; platform_system == "Darwin"
diff --git a/requirements/full/requirements_apple_silicon.txt b/requirements/full/requirements_apple_silicon.txt
index 71da9a67..13df359b 100644
--- a/requirements/full/requirements_apple_silicon.txt
+++ b/requirements/full/requirements_apple_silicon.txt
@@ -40,5 +40,4 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.83.0/llama_cpp_binaries-0.83.0-py3-none-macosx_13_0_arm64.whl; platform_system == "Darwin"
diff --git a/requirements/full/requirements_cpu_only.txt b/requirements/full/requirements_cpu_only.txt
index cd70cb7f..f7ffbca7 100644
--- a/requirements/full/requirements_cpu_only.txt
+++ b/requirements/full/requirements_cpu_only.txt
@@ -39,6 +39,6 @@ flask_cloudflared==0.0.14
 sse-starlette==1.6.5
 tiktoken
 
-# llama.cpp (CPU only, AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"
+# llama.cpp (CPU only)
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.83.0/llama_cpp_binaries-0.83.0+cpu-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.83.0/llama_cpp_binaries-0.83.0+cpu-py3-none-win_amd64.whl; platform_system == "Windows"
diff --git a/requirements/full/requirements_cpu_only_noavx2.txt b/requirements/full/requirements_cpu_only_noavx2.txt
deleted file mode 100644
index 1a128289..00000000
--- a/requirements/full/requirements_cpu_only_noavx2.txt
+++ /dev/null
@@ -1,44 +0,0 @@
-accelerate==1.12.*
-audioop-lts<1.0; python_version >= "3.13"
-colorama
-datasets
-diffusers==0.36.*
-einops
-fastapi==0.112.4
-html2text==2025.4.15
-huggingface-hub==1.5.*
-jinja2==3.1.6
-markdown
-numpy==2.2.*
-pandas
-peft==0.18.*
-Pillow>=9.5.0
-psutil
-pydantic==2.11.0
-PyPDF2==3.0.1
-python-docx==1.1.2
-pyyaml
-requests
-rich
-safetensors==0.7.*
-scipy
-sentencepiece
-tensorboard
-torchao==0.15.*
-transformers==5.2.*
-triton-windows==3.5.1.post24; platform_system == "Windows"
-tqdm
-wandb
-
-# Gradio
-gradio==4.37.*
-https://github.com/oobabooga/gradio/releases/download/custom-build/gradio_client-1.0.2+custom.1-py3-none-any.whl
-
-# API
-flask_cloudflared==0.0.14
-sse-starlette==1.6.5
-tiktoken
-
-# llama.cpp (CPU only, no AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"
diff --git a/requirements/full/requirements_noavx2.txt b/requirements/full/requirements_noavx2.txt
deleted file mode 100644
index e2a9fd58..00000000
--- a/requirements/full/requirements_noavx2.txt
+++ /dev/null
@@ -1,53 +0,0 @@
-accelerate==1.12.*
-audioop-lts<1.0; python_version >= "3.13"
-bitsandbytes==0.49.*
-colorama
-datasets
-diffusers==0.36.*
-einops
-fastapi==0.112.4
-flash-linear-attention==0.4.*
-html2text==2025.4.15
-huggingface-hub==1.5.*
-jinja2==3.1.6
-markdown
-numpy==2.2.*
-pandas
-peft==0.18.*
-Pillow>=9.5.0
-psutil
-pydantic==2.11.0
-PyPDF2==3.0.1
-python-docx==1.1.2
-pyyaml
-requests
-rich
-safetensors==0.7.*
-scipy
-sentencepiece
-tensorboard
-torchao==0.15.*
-transformers==5.2.*
-triton-windows==3.5.1.post24; platform_system == "Windows"
-tqdm
-wandb
-
-# Gradio
-gradio==4.37.*
-https://github.com/oobabooga/gradio/releases/download/custom-build/gradio_client-1.0.2+custom.1-py3-none-any.whl
-
-# API
-flask_cloudflared==0.0.14
-sse-starlette==1.6.5
-tiktoken
-
-# CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/turboderp-org/exllamav3/releases/download/v0.0.22/exllamav3-0.0.22+cu128.torch2.9.0-cp313-cp313-win_amd64.whl; platform_system == "Windows" and python_version == "3.13"
-https://github.com/turboderp-org/exllamav3/releases/download/v0.0.22/exllamav3-0.0.22+cu128.torch2.9.0-cp313-cp313-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.13"
-https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.9.0-cp313-cp313-win_amd64.whl; platform_system == "Windows" and python_version == "3.13"
-https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.9.0-cp313-cp313-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.13"
-https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"
-https://github.com/kingbri1/flash-attention/releases/download/v2.8.3/flash_attn-2.8.3+cu128torch2.9.0cxx11abiFALSE-cp313-cp313-win_amd64.whl; platform_system == "Windows" and python_version == "3.13"
-https://github.com/kingbri1/flash-attention/releases/download/v2.8.3/flash_attn-2.8.3+cu128torch2.9.0cxx11abiFALSE-cp313-cp313-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.13"
diff --git a/requirements/portable/requirements.txt b/requirements/portable/requirements.txt
index b9576255..30e872aa 100644
--- a/requirements/portable/requirements.txt
+++ b/requirements/portable/requirements.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.83.0/llama_cpp_binaries-0.83.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.83.0/llama_cpp_binaries-0.83.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements/portable/requirements_amd.txt b/requirements/portable/requirements_amd.txt
index dc30f421..bd784950 100644
--- a/requirements/portable/requirements_amd.txt
+++ b/requirements/portable/requirements_amd.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # AMD wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+rocm6.4.4-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.83.0/llama_cpp_binaries-0.83.0+rocm6.4-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.83.0/llama_cpp_binaries-0.83.0+rocm6.4-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements/portable/requirements_amd_noavx2.txt b/requirements/portable/requirements_amd_noavx2.txt
deleted file mode 100644
index 34746426..00000000
--- a/requirements/portable/requirements_amd_noavx2.txt
+++ /dev/null
@@ -1,27 +0,0 @@
-audioop-lts<1.0; python_version >= "3.13"
-fastapi==0.112.4
-html2text==2025.4.15
-huggingface-hub==1.5.*
-jinja2==3.1.6
-markdown
-numpy==2.2.*
-pydantic==2.11.0
-PyPDF2==3.0.1
-python-docx==1.1.2
-pyyaml
-requests
-rich
-tqdm
-
-# Gradio
-gradio==4.37.*
-https://github.com/oobabooga/gradio/releases/download/custom-build/gradio_client-1.0.2+custom.1-py3-none-any.whl
-
-# API
-flask_cloudflared==0.0.14
-sse-starlette==1.6.5
-tiktoken
-
-# AMD wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+rocm6.4.4avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements/portable/requirements_apple_intel.txt b/requirements/portable/requirements_apple_intel.txt
index 6bae46d6..274b3a03 100644
--- a/requirements/portable/requirements_apple_intel.txt
+++ b/requirements/portable/requirements_apple_intel.txt
@@ -23,5 +23,4 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.83.0/llama_cpp_binaries-0.83.0-py3-none-macosx_13_0_x86_64.whl; platform_system == "Darwin"
diff --git a/requirements/portable/requirements_apple_silicon.txt b/requirements/portable/requirements_apple_silicon.txt
index 2f9e4dc5..f67c1851 100644
--- a/requirements/portable/requirements_apple_silicon.txt
+++ b/requirements/portable/requirements_apple_silicon.txt
@@ -23,5 +23,4 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.83.0/llama_cpp_binaries-0.83.0-py3-none-macosx_13_0_arm64.whl; platform_system == "Darwin"
diff --git a/requirements/portable/requirements_cpu_only.txt b/requirements/portable/requirements_cpu_only.txt
index 739ac26f..6b48c795 100644
--- a/requirements/portable/requirements_cpu_only.txt
+++ b/requirements/portable/requirements_cpu_only.txt
@@ -22,6 +22,6 @@ flask_cloudflared==0.0.14
 sse-starlette==1.6.5
 tiktoken
 
-# llama.cpp (CPU only, AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"
+# llama.cpp (CPU only)
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.83.0/llama_cpp_binaries-0.83.0+cpu-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.83.0/llama_cpp_binaries-0.83.0+cpu-py3-none-win_amd64.whl; platform_system == "Windows"
diff --git a/requirements/portable/requirements_cpu_only_noavx2.txt b/requirements/portable/requirements_cpu_only_noavx2.txt
deleted file mode 100644
index e096ed1d..00000000
--- a/requirements/portable/requirements_cpu_only_noavx2.txt
+++ /dev/null
@@ -1,27 +0,0 @@
-audioop-lts<1.0; python_version >= "3.13"
-fastapi==0.112.4
-html2text==2025.4.15
-huggingface-hub==1.5.*
-jinja2==3.1.6
-markdown
-numpy==2.2.*
-pydantic==2.11.0
-PyPDF2==3.0.1
-python-docx==1.1.2
-pyyaml
-requests
-rich
-tqdm
-
-# Gradio
-gradio==4.37.*
-https://github.com/oobabooga/gradio/releases/download/custom-build/gradio_client-1.0.2+custom.1-py3-none-any.whl
-
-# API
-flask_cloudflared==0.0.14
-sse-starlette==1.6.5
-tiktoken
-
-# llama.cpp (CPU only, no AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"
diff --git a/requirements/portable/requirements_noavx2.txt b/requirements/portable/requirements_noavx2.txt
deleted file mode 100644
index 12e24ab4..00000000
--- a/requirements/portable/requirements_noavx2.txt
+++ /dev/null
@@ -1,27 +0,0 @@
-audioop-lts<1.0; python_version >= "3.13"
-fastapi==0.112.4
-html2text==2025.4.15
-huggingface-hub==1.5.*
-jinja2==3.1.6
-markdown
-numpy==2.2.*
-pydantic==2.11.0
-PyPDF2==3.0.1
-python-docx==1.1.2
-pyyaml
-requests
-rich
-tqdm
-
-# Gradio
-gradio==4.37.*
-https://github.com/oobabooga/gradio/releases/download/custom-build/gradio_client-1.0.2+custom.1-py3-none-any.whl
-
-# API
-flask_cloudflared==0.0.14
-sse-starlette==1.6.5
-tiktoken
-
-# CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements/portable/requirements_vulkan.txt b/requirements/portable/requirements_vulkan.txt
index c2a66a69..ad059281 100644
--- a/requirements/portable/requirements_vulkan.txt
+++ b/requirements/portable/requirements_vulkan.txt
@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # Vulkan wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.83.0/llama_cpp_binaries-0.83.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.83.0/llama_cpp_binaries-0.83.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements/portable/requirements_vulkan_noavx2.txt b/requirements/portable/requirements_vulkan_noavx2.txt
deleted file mode 100644
index 79b632bb..00000000
--- a/requirements/portable/requirements_vulkan_noavx2.txt
+++ /dev/null
@@ -1,27 +0,0 @@
-audioop-lts<1.0; python_version >= "3.13"
-fastapi==0.112.4
-html2text==2025.4.15
-huggingface-hub==1.5.*
-jinja2==3.1.6
-markdown
-numpy==2.2.*
-pydantic==2.11.0
-PyPDF2==3.0.1
-python-docx==1.1.2
-pyyaml
-requests
-rich
-tqdm
-
-# Gradio
-gradio==4.37.*
-https://github.com/oobabooga/gradio/releases/download/custom-build/gradio_client-1.0.2+custom.1-py3-none-any.whl
-
-# API
-flask_cloudflared==0.0.14
-sse-starlette==1.6.5
-tiktoken
-
-# CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.74.0/llama_cpp_binaries-0.74.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"