Add ik_llama.cpp support via ik_llama_cpp_binaries package

.github/workflows/build-everything-tgw.yml

@@ -68,3 +68,38 @@ jobs:
     with:
       version: ${{ inputs.version }}
       config: 'os:macos-15-intel,macos-14'
+
+  build_release_ik_cuda_windows:
+    name: ik CUDA Windows
+    uses: ./.github/workflows/build-portable-release-ik-cuda.yml
+    with:
+      version: ${{ inputs.version }}
+      config: 'os:windows-2022'
+
+  build_release_ik_cuda_linux:
+    name: ik CUDA Linux
+    uses: ./.github/workflows/build-portable-release-ik-cuda.yml
+    with:
+      version: ${{ inputs.version }}
+      config: 'os:ubuntu-22.04'
+
+  build_release_ik_cpu_windows:
+    name: ik CPU Windows
+    uses: ./.github/workflows/build-portable-release-ik.yml
+    with:
+      version: ${{ inputs.version }}
+      config: 'os:windows-2022'
+
+  build_release_ik_cpu_linux:
+    name: ik CPU Linux
+    uses: ./.github/workflows/build-portable-release-ik.yml
+    with:
+      version: ${{ inputs.version }}
+      config: 'os:ubuntu-22.04'
+
+  build_release_ik_macos:
+    name: ik macOS
+    uses: ./.github/workflows/build-portable-release-ik.yml
+    with:
+      version: ${{ inputs.version }}
+      config: 'os:macos-14'

.github/workflows/build-portable-release-ik-cuda.yml

@@ -0,0 +1,179 @@
+name: Build ik CUDA
+
+on:
+  workflow_dispatch:
+    inputs:
+      version:
+        description: 'Version tag of text-generation-webui to build: v3.0'
+        default: 'v3.0'
+        required: true
+        type: string
+      config:
+        description: 'Override configurations to build: key1:item1-1,item1-2;key2:item2-1,item2-2'
+        default: 'Default'
+        required: false
+        type: string
+      exclude:
+        description: 'Exclude build configurations: key1-1:item1-1,key1-2:item1-2;key2-1:item2-1,key2-2:item2-2'
+        default: 'None'
+        required: false
+        type: string
+  workflow_call:
+    inputs:
+      version:
+        description: 'Version tag of text-generation-webui to build: v3.0'
+        default: 'v3.0'
+        required: true
+        type: string
+      config:
+        description: 'Configurations to build: key1:item1-1,item1-2;key2:item2-1,item2-2'
+        default: 'Default'
+        required: false
+        type: string
+      exclude:
+        description: 'Exclude build configurations: key1-1:item1-1,key1-2:item1-2;key2-1:item2-1,key2-2:item2-2'
+        default: 'None'
+        required: false
+        type: string
+
+permissions:
+  contents: write
+
+jobs:
+  define_matrix:
+    name: Define Build Matrix
+    runs-on: ubuntu-latest
+    outputs:
+      matrix: ${{ steps.set-matrix.outputs.matrix }}
+    defaults:
+      run:
+        shell: pwsh
+    env:
+      CONFIGIN: ${{ inputs.config }}
+      EXCLUDEIN: ${{ inputs.exclude }}
+
+    steps:
+      - name: Define Job Output
+        id: set-matrix
+        run: |
+          $matrix = @{
+              'os' = @('ubuntu-22.04', 'windows-2022')
+              'pyver' = @("3.13")
+              'cuda' = @("12.4", "13.1")
+          }
+
+          if ($env:CONFIGIN -ne 'Default') {$env:CONFIGIN.split(';').foreach({$matrix[$_.split(':')[0]] = $_.split(':')[1].split(',')})}
+
+          if ($env:EXCLUDEIN -ne 'None') {
+              $exclusions = @()
+              $exclusions += $env:EXCLUDEIN.split(';').replace(':','=').replace(',',"`n") | ConvertFrom-StringData
+              $matrix['exclude'] = $exclusions
+          }
+
+          $matrixOut = ConvertTo-Json $matrix -Compress
+          Write-Output ('matrix=' + $matrixOut) >> $env:GITHUB_OUTPUT
+
+  build_wheels:
+    name: ${{ matrix.os }} ${{ matrix.pyver }} CUDA ${{ matrix.cuda }}
+    needs: define_matrix
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix: ${{ fromJSON(needs.define_matrix.outputs.matrix) }}
+    defaults:
+      run:
+        shell: pwsh
+    env:
+      PCKGVER: ${{ inputs.version }}
+
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          repository: 'oobabooga/text-generation-webui'
+          ref: ${{ inputs.version }}
+          submodules: 'recursive'
+
+      - uses: actions/setup-python@v6
+        with:
+          python-version: ${{ matrix.pyver }}
+
+      - name: Build Package
+        shell: bash
+        run: |
+            VERSION_CLEAN="${{ inputs.version }}"
+            VERSION_CLEAN="${VERSION_CLEAN#v}"
+            cd ..
+            cp -r text-generation-webui "text-generation-webui-${VERSION_CLEAN}"
+            cd "text-generation-webui-${VERSION_CLEAN}"
+
+            # Remove extensions that need additional requirements
+            allowed=("character_bias" "gallery" "sd_api_pictures")
+            find extensions/ -mindepth 1 -maxdepth 1 -type d | grep -v -E "$(printf '%s|' "${allowed[@]}" | sed 's/|$//')" | xargs rm -rf
+
+            # Define common variables
+            CUDA_VERSION="${{ matrix.cuda }}"
+            VERSION="${{ inputs.version }}"
+
+            # 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_stripped.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_stripped.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 ..
+            echo "Downloading Python for $PLATFORM..."
+            curl -L -o python-build.tar.gz "$PYTHON_URL"
+            tar -xzf python-build.tar.gz
+            mv python "text-generation-webui-${VERSION_CLEAN}/portable_env"
+
+            # 3. Prepare requirements file based on CUDA version
+            cd "text-generation-webui-${VERSION_CLEAN}"
+            if [[ "$CUDA_VERSION" == "13.1" ]]; then
+                REQ_FILE="requirements/portable/requirements_cuda131.txt"
+            else
+                REQ_FILE="requirements/portable/requirements.txt"
+            fi
+
+            # 4. Swap llama.cpp wheels for ik_llama.cpp and inject --ik into start scripts
+            sed -i 's|/llama_cpp_binaries-|/ik_llama_cpp_binaries-|g' "$REQ_FILE"
+            sed -i 's/--portable/--portable --ik/g' start_linux.sh start_windows.bat start_macos.sh 2>/dev/null || true
+
+            # 5. Install packages
+            echo "Installing Python packages from $REQ_FILE..."
+            $PIP_PATH install --target="./$PACKAGES_PATH" -r "$REQ_FILE"
+
+            # 6. Clean up
+            rm -rf .git cmd* update_wizard* Colab-TextGen-GPU.ipynb docker setup.cfg .github .gitignore requirements/ one_click.py
+
+            # 7. Create archive
+            cd ..
+            if [[ "$RUNNER_OS" == "Windows" ]]; then
+                ARCHIVE_NAME="textgen-portable-ik-${VERSION_CLEAN}-${PLATFORM}-cuda${CUDA_VERSION}.zip"
+                echo "Creating archive: $ARCHIVE_NAME"
+                powershell -Command "Compress-Archive -Path text-generation-webui-${VERSION_CLEAN} -DestinationPath $ARCHIVE_NAME"
+            else
+                ARCHIVE_NAME="textgen-portable-ik-${VERSION_CLEAN}-${PLATFORM}-cuda${CUDA_VERSION}.tar.gz"
+                echo "Creating archive: $ARCHIVE_NAME"
+                tar czf "$ARCHIVE_NAME" "text-generation-webui-${VERSION_CLEAN}"
+            fi
+
+      - name: Upload files to a GitHub release
+        id: upload-release
+        uses: svenstaro/upload-release-action@2.7.0
+        continue-on-error: true
+        with:
+          repo_token: ${{ secrets.GITHUB_TOKEN }}
+          file: ../textgen-portable-ik-*
+          tag: ${{ inputs.version }}
+          file_glob: true
+          make_latest: false
+          overwrite: true

.github/workflows/build-portable-release-ik.yml

@@ -0,0 +1,205 @@
+name: Build ik CPU and macOS
+
+on:
+  workflow_dispatch:
+    inputs:
+      version:
+        description: 'Version tag of text-generation-webui to build: v3.0'
+        default: 'v3.0'
+        required: true
+        type: string
+      config:
+        description: 'Override configurations to build: key1:item1-1,item1-2;key2:item2-1,item2-2'
+        default: 'Default'
+        required: false
+        type: string
+      exclude:
+        description: 'Exclude build configurations: key1-1:item1-1,key1-2:item1-2;key2-1:item2-1,key2-2:item2-2'
+        default: 'None'
+        required: false
+        type: string
+  workflow_call:
+    inputs:
+      version:
+        description: 'Version tag of text-generation-webui to build: v3.0'
+        default: 'v3.0'
+        required: true
+        type: string
+      config:
+        description: 'Configurations to build: key1:item1-1,item1-2;key2:item2-1,item2-2'
+        default: 'Default'
+        required: false
+        type: string
+      exclude:
+        description: 'Exclude build configurations: key1-1:item1-1,key1-2:item1-2;key2-1:item2-1,key2-2:item2-2'
+        default: 'None'
+        required: false
+        type: string
+
+permissions:
+  contents: write
+
+jobs:
+  define_matrix:
+    name: Define Build Matrix
+    runs-on: ubuntu-latest
+    outputs:
+      matrix: ${{ steps.set-matrix.outputs.matrix }}
+    defaults:
+      run:
+        shell: pwsh
+    env:
+      CONFIGIN: ${{ inputs.config }}
+      EXCLUDEIN: ${{ inputs.exclude }}
+
+    steps:
+      - name: Define Job Output
+        id: set-matrix
+        run: |
+          $matrix = @{
+              'os' = @('ubuntu-22.04', 'windows-2022', 'macos-14')
+              'pyver' = @("3.13")
+          }
+
+          if ($env:CONFIGIN -ne 'Default') {$env:CONFIGIN.split(';').foreach({$matrix[$_.split(':')[0]] = $_.split(':')[1].split(',')})}
+
+          if ($env:EXCLUDEIN -ne 'None') {
+              $exclusions = @()
+              $exclusions += $env:EXCLUDEIN.split(';').replace(':','=').replace(',',"`n") | ConvertFrom-StringData
+              $matrix['exclude'] = $exclusions
+          }
+
+          $matrixOut = ConvertTo-Json $matrix -Compress
+          Write-Output ('matrix=' + $matrixOut) >> $env:GITHUB_OUTPUT
+
+  build_wheels:
+    name: ${{ matrix.os }} ${{ matrix.pyver }}
+    needs: define_matrix
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix: ${{ fromJSON(needs.define_matrix.outputs.matrix) }}
+    defaults:
+      run:
+        shell: pwsh
+    env:
+      PCKGVER: ${{ inputs.version }}
+
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          repository: 'oobabooga/text-generation-webui'
+          ref: ${{ inputs.version }}
+          submodules: 'recursive'
+
+      - uses: actions/setup-python@v6
+        with:
+          python-version: ${{ matrix.pyver }}
+
+      - name: Build Package
+        shell: bash
+        run: |
+            VERSION_CLEAN="${{ inputs.version }}"
+            VERSION_CLEAN="${VERSION_CLEAN#v}"
+            cd ..
+            cp -r text-generation-webui "text-generation-webui-${VERSION_CLEAN}"
+            cd "text-generation-webui-${VERSION_CLEAN}"
+
+            # Remove extensions that need additional requirements
+            allowed=("character_bias" "gallery" "sd_api_pictures")
+            find extensions/ -mindepth 1 -maxdepth 1 -type d | grep -v -E "$(printf '%s|' "${allowed[@]}" | sed 's/|$//')" | xargs rm -rf
+
+            # Define common variables
+            VERSION="${{ inputs.version }}"
+            OS_TYPE="${{ matrix.os }}"
+
+            # 1. Set platform-specific variables
+            if [[ "$RUNNER_OS" == "Windows" ]]; then
+                PLATFORM="windows-cpu"
+                PYTHON_URL="https://github.com/astral-sh/python-build-standalone/releases/download/20260303/cpython-3.13.12+20260303-x86_64-pc-windows-msvc-install_only_stripped.tar.gz"
+                PIP_PATH="portable_env/python.exe -m pip"
+                PACKAGES_PATH="portable_env/Lib/site-packages"
+                rm start_linux.sh start_macos.sh
+            elif [[ "$RUNNER_OS" == "macOS" ]]; then
+                if [[ "$OS_TYPE" == "macos-15-intel" ]]; then
+                    PLATFORM="macos-x86_64"
+                    PYTHON_URL="https://github.com/astral-sh/python-build-standalone/releases/download/20260303/cpython-3.13.12+20260303-x86_64-apple-darwin-install_only_stripped.tar.gz"
+                    REQ_TYPE="apple_intel"
+                else
+                    PLATFORM="macos-arm64"
+                    PYTHON_URL="https://github.com/astral-sh/python-build-standalone/releases/download/20260303/cpython-3.13.12+20260303-aarch64-apple-darwin-install_only_stripped.tar.gz"
+                    REQ_TYPE="apple_silicon"
+                fi
+                PIP_PATH="portable_env/bin/python -m pip"
+                PACKAGES_PATH="portable_env/lib/python3.13/site-packages"
+                rm start_linux.sh start_windows.bat
+            else
+                # Linux case
+                PLATFORM="linux-cpu"
+                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_stripped.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
+            echo "Downloading Python for $PLATFORM..."
+            cd ..
+            curl -L -o python-build.tar.gz "$PYTHON_URL"
+            tar -xzf python-build.tar.gz
+            mv python "text-generation-webui-${VERSION_CLEAN}/portable_env"
+
+            # 3. Prepare requirements file based on platform
+            cd "text-generation-webui-${VERSION_CLEAN}"
+
+            # Select requirements file based on platform
+            if [[ "$RUNNER_OS" == "macOS" ]]; then
+                if [[ "$OS_TYPE" == "macos-15-intel" ]]; then
+                    REQ_FILE="requirements/portable/requirements_apple_intel.txt"
+                else
+                    REQ_FILE="requirements/portable/requirements_apple_silicon.txt"
+                fi
+            else
+                REQ_FILE="requirements/portable/requirements_cpu_only.txt"
+            fi
+
+            echo "Using requirements file: $REQ_FILE"
+
+            # 4. Swap llama.cpp wheels for ik_llama.cpp and inject --ik into start scripts
+            if [[ "$RUNNER_OS" == "macOS" ]]; then
+                sed -i '' 's|/llama_cpp_binaries-|/ik_llama_cpp_binaries-|g' "$REQ_FILE"
+                sed -i '' 's/--portable/--portable --ik/g' start_macos.sh
+            else
+                sed -i 's|/llama_cpp_binaries-|/ik_llama_cpp_binaries-|g' "$REQ_FILE"
+                sed -i 's/--portable/--portable --ik/g' start_linux.sh start_windows.bat 2>/dev/null || true
+            fi
+
+            # 5. Install packages
+            echo "Installing Python packages from $REQ_FILE..."
+            $PIP_PATH install --target="./$PACKAGES_PATH" -r "$REQ_FILE"
+
+            # 6. Clean up
+            rm -rf .git cmd* update_wizard* Colab-TextGen-GPU.ipynb docker setup.cfg .github .gitignore requirements/ one_click.py
+
+            # 7. Create archive
+            cd ..
+            if [[ "$RUNNER_OS" == "Windows" ]]; then
+                ARCHIVE_NAME="textgen-portable-ik-${VERSION_CLEAN}-${PLATFORM}.zip"
+                echo "Creating archive: $ARCHIVE_NAME"
+                powershell -Command "Compress-Archive -Path text-generation-webui-${VERSION_CLEAN} -DestinationPath $ARCHIVE_NAME"
+            else
+                ARCHIVE_NAME="textgen-portable-ik-${VERSION_CLEAN}-${PLATFORM}.tar.gz"
+                echo "Creating archive: $ARCHIVE_NAME"
+                tar czf "$ARCHIVE_NAME" "text-generation-webui-${VERSION_CLEAN}"
+            fi
+
+      - name: Upload files to a GitHub release
+        id: upload-release
+        uses: svenstaro/upload-release-action@2.7.0
+        continue-on-error: true
+        with:
+          repo_token: ${{ secrets.GITHUB_TOKEN }}
+          file: ../textgen-portable-ik-*
+          tag: ${{ inputs.version }}
+          file_glob: true
+          make_latest: false
+          overwrite: true

modules/llama_cpp_server.py

@@ -11,7 +11,6 @@ import time
 from pathlib import Path
 from typing import Any, List
 
-import llama_cpp_binaries
 import requests
 
 from modules import shared
@@ -357,7 +356,16 @@ class LlamaServer:
         """Start the llama.cpp server and wait until it's ready."""
         # Determine the server path
         if self.server_path is None:
-            self.server_path = llama_cpp_binaries.get_binary_path()
+            if shared.args.ik:
+                try:
+                    import ik_llama_cpp_binaries
+                except ImportError:
+                    raise ImportError("--ik requires the ik_llama_cpp_binaries package. Install it with: pip install <ik_llama_cpp_binaries wheel URL>")
+
+                self.server_path = ik_llama_cpp_binaries.get_binary_path()
+            else:
+                import llama_cpp_binaries
+                self.server_path = llama_cpp_binaries.get_binary_path()
 
         # Build the command
         cmd = [
@@ -616,10 +624,12 @@ def filter_stderr_with_progress(process_stderr):
 def _patch_cmd_for_ik(cmd):
     """
     Rewrite upstream llama.cpp flags to ik_llama.cpp equivalents:
-      --no-webui          → --webui none
+      --no-webui           → --webui none
       --fit off            → (removed)
       --fit on / --fit-ctx → --fit (bare flag)
       --fit-target         → --fit-margin
+      --cache-reuse        → (removed, unsupported)
+      --swa-full           → (removed, unsupported)
     """
     patched = []
     i = 0
@@ -635,9 +645,14 @@ def _patch_cmd_for_ik(cmd):
                 patched.append("--fit")
             # "off" → drop entirely
         elif arg == "--fit-ctx":
+            patched.append("--fit")
             i += 1  # skip the value
         elif arg == "--fit-target":
             patched.append("--fit-margin")
+        elif arg == "--cache-reuse":
+            i += 1  # skip the value
+        elif arg == "--swa-full":
+            pass  # bare flag, just drop it
         else:
             patched.append(arg)
 

modules/loaders.py

@@ -20,6 +20,7 @@ loaders_and_params = OrderedDict({
         'no_mmap',
         'mlock',
         'numa',
+        'ik',
         'parallel',
         'model_draft',
         'draft_max',
@@ -345,6 +346,7 @@ def list_model_elements():
         'spec_ngram_size_m',
         'spec_ngram_min_hits',
         'mmproj',
+        'ik',
     ]
 
 

modules/shared.py

@@ -110,7 +110,7 @@ group.add_argument('--numa', action='store_true', help='Activate NUMA task alloc
 group.add_argument('--parallel', type=int, default=1, help='Number of parallel request slots. The context size is divided equally among slots. For example, to have 4 slots with 8192 context each, set ctx_size to 32768.')
 group.add_argument('--fit-target', type=str, default='512', help='Target VRAM margin per device for auto GPU layers, comma-separated list of values in MiB. A single value is broadcast across all devices.')
 group.add_argument('--extra-flags', type=str, default=None, help='Extra flags to pass to llama-server. Example: "--jinja --rpc 192.168.1.100:50052"')
-group.add_argument('--ik', action='store_true', help='Use ik_llama.cpp instead of upstream llama.cpp. To install: build ik_llama.cpp, then delete all files inside <venv>/lib/pythonX.Y/site-packages/llama_cpp_binaries/bin/ and copy or symlink the ik_llama.cpp build outputs into that folder.')
+group.add_argument('--ik', action='store_true', help='Use ik_llama.cpp instead of upstream llama.cpp. Requires the ik_llama_cpp_binaries package to be installed.')
 
 # Transformers/Accelerate
 group = parser.add_argument_group('Transformers/Accelerate')

modules/ui_model_menu.py

@@ -51,6 +51,9 @@ def create_ui():
 
                         with gr.Column():
                             shared.gradio['vram_info'] = gr.HTML(value=get_initial_vram_info())
+                            if not shared.args.portable:
+                                shared.gradio['ik'] = gr.Checkbox(label="ik", value=shared.args.ik, info='Use ik_llama.cpp instead of upstream llama.cpp.')
+
                             shared.gradio['cpu_moe'] = gr.Checkbox(label="cpu-moe", value=shared.args.cpu_moe, info='Move the experts to the CPU. Saves VRAM on MoE models.')
                             shared.gradio['streaming_llm'] = gr.Checkbox(label="streaming-llm", value=shared.args.streaming_llm, info='Activate StreamingLLM to avoid re-evaluating the entire prompt when old messages are removed.')
                             shared.gradio['load_in_8bit'] = gr.Checkbox(label="load-in-8bit", value=shared.args.load_in_8bit)

requirements/full/requirements.txt

@@ -40,8 +40,10 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.98.0/llama_cpp_binaries-0.98.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.98.0/llama_cpp_binaries-0.98.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.99.0/llama_cpp_binaries-0.99.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.99.0/llama_cpp_binaries-0.99.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.99.0/ik_llama_cpp_binaries-0.99.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.99.0/ik_llama_cpp_binaries-0.99.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/turboderp-org/exllamav3/releases/download/v0.0.26/exllamav3-0.0.26+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/v0.0.26/exllamav3-0.0.26+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/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"

requirements/full/requirements_amd.txt

@@ -37,5 +37,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # AMD wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.98.0/llama_cpp_binaries-0.98.0+rocm7.2-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.98.0/llama_cpp_binaries-0.98.0+rocm7.2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.99.0/llama_cpp_binaries-0.99.0+rocm7.2-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.99.0/llama_cpp_binaries-0.99.0+rocm7.2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

requirements/full/requirements_apple_intel.txt

@@ -37,4 +37,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.98.0/llama_cpp_binaries-0.98.0-py3-none-macosx_13_0_x86_64.whl; platform_system == "Darwin"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.99.0/llama_cpp_binaries-0.99.0-py3-none-macosx_13_0_x86_64.whl; platform_system == "Darwin"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.99.0/ik_llama_cpp_binaries-0.99.0-py3-none-macosx_13_0_x86_64.whl; platform_system == "Darwin"

requirements/full/requirements_apple_silicon.txt

@@ -37,4 +37,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.98.0/llama_cpp_binaries-0.98.0-py3-none-macosx_13_0_arm64.whl; platform_system == "Darwin"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.99.0/llama_cpp_binaries-0.99.0-py3-none-macosx_13_0_arm64.whl; platform_system == "Darwin"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.99.0/ik_llama_cpp_binaries-0.99.0-py3-none-macosx_13_0_arm64.whl; platform_system == "Darwin"

requirements/full/requirements_cpu_only.txt

@@ -37,5 +37,7 @@ sse-starlette==1.6.5
 tiktoken
 
 # llama.cpp (CPU only)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.98.0/llama_cpp_binaries-0.98.0+cpu-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.98.0/llama_cpp_binaries-0.98.0+cpu-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.99.0/llama_cpp_binaries-0.99.0+cpu-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.99.0/llama_cpp_binaries-0.99.0+cpu-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.99.0/ik_llama_cpp_binaries-0.99.0+cpu-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.99.0/ik_llama_cpp_binaries-0.99.0+cpu-py3-none-win_amd64.whl; platform_system == "Windows"

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/v0.98.0/llama_cpp_binaries-0.98.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.98.0/llama_cpp_binaries-0.98.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.99.0/llama_cpp_binaries-0.99.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.99.0/llama_cpp_binaries-0.99.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

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/v0.98.0/llama_cpp_binaries-0.98.0+rocm7.2-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.98.0/llama_cpp_binaries-0.98.0+rocm7.2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.99.0/llama_cpp_binaries-0.99.0+rocm7.2-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.99.0/llama_cpp_binaries-0.99.0+rocm7.2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

requirements/portable/requirements_apple_intel.txt

@@ -23,4 +23,4 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.98.0/llama_cpp_binaries-0.98.0-py3-none-macosx_13_0_x86_64.whl; platform_system == "Darwin"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.99.0/llama_cpp_binaries-0.99.0-py3-none-macosx_13_0_x86_64.whl; platform_system == "Darwin"

requirements/portable/requirements_apple_silicon.txt

@@ -23,4 +23,4 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.98.0/llama_cpp_binaries-0.98.0-py3-none-macosx_13_0_arm64.whl; platform_system == "Darwin"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.99.0/llama_cpp_binaries-0.99.0-py3-none-macosx_13_0_arm64.whl; platform_system == "Darwin"

requirements/portable/requirements_cpu_only.txt

@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # llama.cpp (CPU only)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.98.0/llama_cpp_binaries-0.98.0+cpu-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.98.0/llama_cpp_binaries-0.98.0+cpu-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.99.0/llama_cpp_binaries-0.99.0+cpu-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.99.0/llama_cpp_binaries-0.99.0+cpu-py3-none-win_amd64.whl; platform_system == "Windows"

requirements/portable/requirements_cuda131.txt

@@ -23,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.98.0/llama_cpp_binaries-0.98.0+cu131-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.98.0/llama_cpp_binaries-0.98.0+cu131-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.99.0/llama_cpp_binaries-0.99.0+cu131-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.99.0/llama_cpp_binaries-0.99.0+cu131-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

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/v0.98.0/llama_cpp_binaries-0.98.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.98.0/llama_cpp_binaries-0.98.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.99.0/llama_cpp_binaries-0.99.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.99.0/llama_cpp_binaries-0.99.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"