Merge pull request #5404 from oobabooga/dev

Merge dev branch
2024-11-27 01:59:14 +01:00 · 2024-01-30 14:17:08 -03:00 · 2024-01-30 14:17:08 -03:00 · 4f3fdf1b5f
commit 4f3fdf1b5f
parent e7a760e6b3 167ee72d4e
25 changed files with 336 additions and 235 deletions
--- a/Colab-TextGen-GPU.ipynb
+++ b/Colab-TextGen-GPU.ipynb
@ -65,12 +65,9 @@
        "  torver = torch.__version__\n",
        "  print(f\"TORCH: {torver}\")\n",
        "  is_cuda118 = '+cu118' in torver  # 2.1.0+cu118\n",
-        "  is_cuda117 = '+cu117' in torver  # 2.0.1+cu117\n",
        "\n",
        "  textgen_requirements = open('requirements.txt').read().splitlines()\n",
-        "  if is_cuda117:\n",
-        "      textgen_requirements = [req.replace('+cu121', '+cu117').replace('+cu122', '+cu117').replace('torch2.1', 'torch2.0') for req in textgen_requirements]\n",
-        "  elif is_cuda118:\n",
+        "  if is_cuda118:\n",
        "      textgen_requirements = [req.replace('+cu121', '+cu118').replace('+cu122', '+cu118') for req in textgen_requirements]\n",
        "  with open('temp_requirements.txt', 'w') as file:\n",
        "      file.write('\\n'.join(textgen_requirements))\n",
--- a/README.md
+++ b/README.md
@ -160,12 +160,23 @@ The `requirements*.txt` above contain various wheels precompiled through GitHub
 ### Alternative: Docker

 ```
-ln -s docker/{nvidia/Dockerfile,docker-compose.yml,.dockerignore} .
+For NVIDIA GPU:
+ln -s docker/{nvidia/Dockerfile,nvidia/docker-compose.yml,.dockerignore} .
+For AMD GPU: 
+ln -s docker/{amd/Dockerfile,intel/docker-compose.yml,.dockerignore} .
+For Intel GPU:
+ln -s docker/{intel/Dockerfile,amd/docker-compose.yml,.dockerignore} .
+For CPU only
+ln -s docker/{cpu/Dockerfile,cpu/docker-compose.yml,.dockerignore} .
 cp docker/.env.example .env
+#Create logs/cache dir : 
+mkdir -p logs cache
 # Edit .env and set: 
 #   TORCH_CUDA_ARCH_LIST based on your GPU model
 #   APP_RUNTIME_GID      your host user's group id (run `id -g` in a terminal)
 #   BUILD_EXTENIONS      optionally add comma separated list of extensions to build
+# Edit CMD_FLAGS.txt and add in it the options you want to execute (like --listen --cpu)
+# 
 docker compose up --build
 ```

--- a/docker/.env.example
+++ b/docker/.env.example
@ -20,3 +20,6 @@ APP_RUNTIME_GID=6972
 # override default app build permissions (handy for deploying to cloud)
 #APP_GID=6972
 #APP_UID=6972
+# Set cache env
+TRANSFORMERS_CACHE=/home/app/text-generation-webui/cache/
+HF_HOME=/home/app/text-generation-webui/cache/
--- a/docker/amd/Dockerfile
+++ b/docker/amd/Dockerfile
@ -0,0 +1,21 @@
+# BUILDER
+FROM ubuntu:22.04
+WORKDIR /builder
+ARG TORCH_CUDA_ARCH_LIST="${TORCH_CUDA_ARCH_LIST:-3.5;5.0;6.0;6.1;7.0;7.5;8.0;8.6+PTX}"
+ARG BUILD_EXTENSIONS="${BUILD_EXTENSIONS:-}"
+ARG APP_UID="${APP_UID:-6972}"
+ARG APP_GID="${APP_GID:-6972}"
+
+RUN --mount=type=cache,target=/var/cache/apt,sharing=locked,rw \
+    apt update && \
+    apt install --no-install-recommends -y git vim build-essential python3-dev pip bash curl && \
+    rm -rf /var/lib/apt/lists/*
+WORKDIR /home/app/
+RUN git clone https://github.com/oobabooga/text-generation-webui.git 
+WORKDIR /home/app/text-generation-webui
+RUN GPU_CHOICE=B USE_CUDA118=FALSE LAUNCH_AFTER_INSTALL=FALSE INSTALL_EXTENSIONS=TRUE ./start_linux.sh --verbose
+COPY CMD_FLAGS.txt /home/app/text-generation-webui/
+EXPOSE ${CONTAINER_PORT:-7860} ${CONTAINER_API_PORT:-5000} ${CONTAINER_API_STREAM_PORT:-5005}
+WORKDIR /home/app/text-generation-webui
+# set umask to ensure group read / write at runtime
+CMD umask 0002 && export HOME=/home/app/text-generation-webui && ./start_linux.sh
--- a/docker/amd/docker-compose.yml
+++ b/docker/amd/docker-compose.yml
@ -0,0 +1,57 @@
+version: "3.3"
+services:
+  text-generation-webui:
+    build:
+      context: .
+      args:
+        # 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` |
+        # Default: requirements.txt`
+        # BUILD_REQUIREMENTS: requirements.txt
+        
+        # Extension requirements to build: 
+        # BUILD_EXTENSIONS: 
+        
+        # specify which cuda version your card supports: https://developer.nvidia.com/cuda-gpus
+        TORCH_CUDA_ARCH_LIST: ${TORCH_CUDA_ARCH_LIST:-7.5} 
+        BUILD_EXTENSIONS: ${BUILD_EXTENSIONS:-}
+        APP_GID: ${APP_GID:-6972} 
+        APP_UID: ${APP_UID-6972} 
+    env_file: .env
+    user: "${APP_RUNTIME_UID:-6972}:${APP_RUNTIME_GID:-6972}"
+    ports:
+      - "${HOST_PORT:-7860}:${CONTAINER_PORT:-7860}"
+      - "${HOST_API_PORT:-5000}:${CONTAINER_API_PORT:-5000}"
+    stdin_open: true
+    group_add:
+      - video
+    tty: true
+    ipc: host
+    devices:
+      - /dev/kfd
+      - /dev/dri 
+    cap_add: 
+      - SYS_PTRACE
+    security_opt:
+      - seccomp=unconfined
+    volumes:
+      - ./cache:/home/app/text-generation-webui/cache
+      - ./characters:/home/app/text-generation-webui/characters
+      - ./extensions:/home/app/text-generation-webui/extensions
+      - ./loras:/home/app/text-generation-webui/loras
+      - ./logs:/home/app/text-generation-webui/logs
+      - ./models:/home/app/text-generation-webui/models
+      - ./presets:/home/app/text-generation-webui/presets
+      - ./prompts:/home/app/text-generation-webui/prompts
+      - ./softprompts:/home/app/text-generation-webui/softprompts
+      - ./training:/home/app/text-generation-webui/training
+      - ./cloudflared:/etc/cloudflared
--- a/docker/cpu/Dockerfile
+++ b/docker/cpu/Dockerfile
@ -0,0 +1,25 @@
+# BUILDER
+FROM ubuntu:22.04
+WORKDIR /builder
+ARG TORCH_CUDA_ARCH_LIST="${TORCH_CUDA_ARCH_LIST:-3.5;5.0;6.0;6.1;7.0;7.5;8.0;8.6+PTX}"
+ARG BUILD_EXTENSIONS="${BUILD_EXTENSIONS:-}"
+ARG APP_UID="${APP_UID:-6972}"
+ARG APP_GID="${APP_GID:-6972}"
+ARG GPU_CHOICE=A
+ARG USE_CUDA118=FALSE 
+ARG LAUNCH_AFTER_INSTALL=FALSE 	
+ARG INSTALL_EXTENSIONS=TRUE
+
+RUN --mount=type=cache,target=/var/cache/apt,sharing=locked,rw \
+    apt update && \
+    apt install --no-install-recommends -y git vim build-essential python3-dev pip bash curl && \
+    rm -rf /var/lib/apt/lists/*
+WORKDIR /home/app/
+RUN git clone https://github.com/oobabooga/text-generation-webui.git 
+WORKDIR /home/app/text-generation-webui
+RUN GPU_CHOICE=N USE_CUDA118=FALSE LAUNCH_AFTER_INSTALL=FALSE INSTALL_EXTENSIONS=TRUE ./start_linux.sh --verbose
+COPY CMD_FLAGS.txt /home/app/text-generation-webui/
+EXPOSE ${CONTAINER_PORT:-7860} ${CONTAINER_API_PORT:-5000} ${CONTAINER_API_STREAM_PORT:-5005}
+# set umask to ensure group read / write at runtime
+WORKDIR /home/app/text-generation-webui
+CMD umask 0002 && export HOME=/home/app/text-generation-webui && ./start_linux.sh
--- a/docker/cpu/docker-compose.yml
+++ b/docker/cpu/docker-compose.yml
@ -0,0 +1,47 @@
+version: "3.3"
+services:
+  text-generation-webui:
+    build:
+      context: .
+      args:
+        # 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` |
+        # Default: requirements.txt`
+        # BUILD_REQUIREMENTS: requirements.txt
+        
+        # Extension requirements to build: 
+        # BUILD_EXTENSIONS: 
+        
+        # specify which cuda version your card supports: https://developer.nvidia.com/cuda-gpus
+        TORCH_CUDA_ARCH_LIST: ${TORCH_CUDA_ARCH_LIST:-7.5} 
+        BUILD_EXTENSIONS: ${BUILD_EXTENSIONS:-}
+        APP_GID: ${APP_GID:-6972} 
+        APP_UID: ${APP_UID-6972} 
+    env_file: .env
+    user: "${APP_RUNTIME_UID:-6972}:${APP_RUNTIME_GID:-6972}"
+    ports:
+      - "${HOST_PORT:-7860}:${CONTAINER_PORT:-7860}"
+      - "${HOST_API_PORT:-5000}:${CONTAINER_API_PORT:-5000}"
+    stdin_open: true
+    tty: true
+    volumes:
+      - ./cache:/home/app/text-generation-webui/cache
+      - ./characters:/home/app/text-generation-webui/characters
+      - ./extensions:/home/app/text-generation-webui/extensions
+      - ./loras:/home/app/text-generation-webui/loras
+      - ./logs:/home/app/text-generation-webui/logs
+      - ./models:/home/app/text-generation-webui/models
+      - ./presets:/home/app/text-generation-webui/presets
+      - ./prompts:/home/app/text-generation-webui/prompts
+      - ./softprompts:/home/app/text-generation-webui/softprompts
+      - ./training:/home/app/text-generation-webui/training
+      - ./cloudflared:/etc/cloudflared
--- a/docker/intel/Dockerfile
+++ b/docker/intel/Dockerfile
@ -0,0 +1,21 @@
+# BUILDER
+FROM ubuntu:22.04
+WORKDIR /builder
+ARG TORCH_CUDA_ARCH_LIST="${TORCH_CUDA_ARCH_LIST:-3.5;5.0;6.0;6.1;7.0;7.5;8.0;8.6+PTX}"
+ARG BUILD_EXTENSIONS="${BUILD_EXTENSIONS:-}"
+ARG APP_UID="${APP_UID:-6972}"
+ARG APP_GID="${APP_GID:-6972}"
+
+RUN --mount=type=cache,target=/var/cache/apt,sharing=locked,rw \
+    apt update && \
+    apt install --no-install-recommends -y git vim build-essential python3-dev pip bash curl && \
+    rm -rf /var/lib/apt/lists/*
+WORKDIR /home/app/
+RUN git clone https://github.com/oobabooga/text-generation-webui.git 
+WORKDIR /home/app/text-generation-webui
+RUN GPU_CHOICE=D USE_CUDA118=FALSE LAUNCH_AFTER_INSTALL=FALSE INSTALL_EXTENSIONS=TRUE ./start_linux.sh --verbose
+COPY CMD_FLAGS.txt /home/app/text-generation-webui/
+EXPOSE ${CONTAINER_PORT:-7860} ${CONTAINER_API_PORT:-5000} ${CONTAINER_API_STREAM_PORT:-5005}
+# set umask to ensure group read / write at runtime
+WORKDIR /home/app/text-generation-webui
+CMD umask 0002 && export HOME=/home/app/text-generation-webui && ./start_linux.sh
--- a/docker/intel/docker-compose.yml
+++ b/docker/intel/docker-compose.yml
@ -0,0 +1,55 @@
+version: "3.3"
+services:
+  text-generation-webui:
+    build:
+      context: .
+      args:
+        # 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` |
+        # Default: requirements.txt`
+        # BUILD_REQUIREMENTS: requirements.txt
+        
+        # Extension requirements to build: 
+        # BUILD_EXTENSIONS: 
+        
+        # specify which cuda version your card supports: https://developer.nvidia.com/cuda-gpus
+        TORCH_CUDA_ARCH_LIST: ${TORCH_CUDA_ARCH_LIST:-7.5} 
+        BUILD_EXTENSIONS: ${BUILD_EXTENSIONS:-}
+        APP_GID: ${APP_GID:-6972} 
+        APP_UID: ${APP_UID-6972} 
+    env_file: .env
+    user: "${APP_RUNTIME_UID:-6972}:${APP_RUNTIME_GID:-6972}"
+    ports:
+      - "${HOST_PORT:-7860}:${CONTAINER_PORT:-7860}"
+      - "${HOST_API_PORT:-5000}:${CONTAINER_API_PORT:-5000}"
+    stdin_open: true
+    group_add:
+      - video
+    tty: true
+    ipc: host
+    devices:
+      - /dev/kfd
+      - /dev/dri 
+    cap_add: 
+      - SYS_PTRACE
+    security_opt:
+      - seccomp=unconfined
+    volumes:
+      - ./characters:/home/app/text-generation-webui/characters
+      - ./extensions:/home/app/text-generation-webui/extensions
+      - ./loras:/home/app/text-generation-webui/loras
+      - ./models:/home/app/text-generation-webui/models
+      - ./presets:/home/app/text-generation-webui/presets
+      - ./prompts:/home/app/text-generation-webui/prompts
+      - ./softprompts:/home/app/text-generation-webui/softprompts
+      - ./training:/home/app/text-generation-webui/training
+      - ./cloudflared:/etc/cloudflared
--- a/docker/nvidia/Dockerfile
+++ b/docker/nvidia/Dockerfile
@ -1,57 +1,21 @@
 # BUILDER
-FROM nvidia/cuda:12.1.1-devel-ubuntu22.04 as builder
+FROM ubuntu:22.04
 WORKDIR /builder
 ARG TORCH_CUDA_ARCH_LIST="${TORCH_CUDA_ARCH_LIST:-3.5;5.0;6.0;6.1;7.0;7.5;8.0;8.6+PTX}"
 ARG BUILD_EXTENSIONS="${BUILD_EXTENSIONS:-}"
-ARG BUILD_REQUIREMENTS="${BUILD_REQUIREMENTS:-requirements.txt}"
 ARG APP_UID="${APP_UID:-6972}"
 ARG APP_GID="${APP_GID:-6972}"
-# create / update build env
-RUN --mount=type=cache,target=/var/cache/apt,sharing=locked,rw \
-    apt update && \
-    apt install --no-install-recommends -y git vim build-essential python3-dev pip && \
-    rm -rf /var/lib/apt/lists/*
-RUN --mount=type=cache,target=/root/.cache/pip,rw \
-    pip3 install --global --upgrade pip wheel setuptools && \
-    # make shared builder & runtime app user
-    addgroup --gid $APP_GID app_grp && \
-    useradd -m -u $APP_UID --gid app_grp app
-USER app:app_grp
-# build wheels for runtime
-WORKDIR /home/app/build
-COPY --chown=app:app_grp "$BUILD_REQUIREMENTS" /home/app/build/requirements.txt
-COPY --chown=app:app_grp extensions /home/app/build/extensions
-RUN --mount=type=cache,target=/root/.cache/pip,rw \
-    # build all requirements files as wheel dists
-    pip3 wheel -w wheels -r requirements.txt `echo "$BUILD_EXTENSIONS" | sed -r 's/([^,]+)\s*,?\s*/ -r \/home\/app\/build\/extensions\/\1\/requirements.txt/g'`
-    # drop wheel and setuptools .whl to avoid install issues
-RUN rm wheels/setuptools*.whl

-# RUNTIME
-FROM nvidia/cuda:12.1.1-runtime-ubuntu22.04
-ARG TORCH_CUDA_ARCH_LIST="${TORCH_CUDA_ARCH_LIST:-3.5;5.0;6.0;6.1;7.0;7.5;8.0;8.6}"
-ARG APP_UID="${APP_UID:-6972}"
-ARG APP_GID="${APP_GID:-6972}"
-ENV CLI_ARGS=""
-# create / update runtime env
 RUN --mount=type=cache,target=/var/cache/apt,sharing=locked,rw \
    apt update && \
-    apt install --no-install-recommends -y git python3 pip && \
-    rm -rf /var/lib/apt/lists/* && \
-    pip3 install --global --no-cache --upgrade pip wheel setuptools && \
-    # make shared builder & runtime app user
-    addgroup --gid $APP_GID app_grp && \
-    useradd -m -u $APP_UID --gid app_grp app
-USER app:app_grp
-# install locally built wheels for app
-WORKDIR /home/app/wheels
-COPY --from=builder /home/app/build/wheels /home/app/wheels
-COPY --chown=app:app_grp . /home/app/text-generation-webui
-RUN umask 0002 && \
-    chmod g+rwX /home/app/text-generation-webui && \
-    pip3 install --global --no-build-isolation --no-cache --no-index ./*.whl && \
-    rm -r /home/app/wheels
+    apt install --no-install-recommends -y git vim build-essential python3-dev pip bash curl && \
+    rm -rf /var/lib/apt/lists/*
+WORKDIR /home/app/
+RUN git clone https://github.com/oobabooga/text-generation-webui.git 
 WORKDIR /home/app/text-generation-webui
+RUN GPU_CHOICE=A USE_CUDA118=FALSE LAUNCH_AFTER_INSTALL=FALSE INSTALL_EXTENSIONS=TRUE ./start_linux.sh --verbose
+COPY CMD_FLAGS.txt /home/app/text-generation-webui/
 EXPOSE ${CONTAINER_PORT:-7860} ${CONTAINER_API_PORT:-5000} ${CONTAINER_API_STREAM_PORT:-5005}
+WORKDIR /home/app/text-generation-webui
 # set umask to ensure group read / write at runtime
-CMD umask 0002 && export HOME=/home/app && python3 server.py ${CLI_ARGS}
+CMD umask 0002 && export HOME=/home/app/text-generation-webui && ./start_linux.sh
--- a/docker/nvidia/docker-compose.yml
+++ b/docker/nvidia/docker-compose.yml
@ -34,9 +34,11 @@ services:
    stdin_open: true
    tty: true
    volumes:
+      - ./cache:/home/app/text-generation-webui/cache
      - ./characters:/home/app/text-generation-webui/characters
      - ./extensions:/home/app/text-generation-webui/extensions
      - ./loras:/home/app/text-generation-webui/loras
+      - ./logs:/home/app/text-generation-webui/logs
      - ./models:/home/app/text-generation-webui/models
      - ./presets:/home/app/text-generation-webui/presets
      - ./prompts:/home/app/text-generation-webui/prompts
--- a/download-model.py
+++ b/download-model.py
@ -30,10 +30,18 @@ class ModelDownloader:
        if max_retries:
            self.session.mount('https://cdn-lfs.huggingface.co', HTTPAdapter(max_retries=max_retries))
            self.session.mount('https://huggingface.co', HTTPAdapter(max_retries=max_retries))
+
        if os.getenv('HF_USER') is not None and os.getenv('HF_PASS') is not None:
            self.session.auth = (os.getenv('HF_USER'), os.getenv('HF_PASS'))
-        if os.getenv('HF_TOKEN') is not None:
-            self.session.headers = {'authorization': f'Bearer {os.getenv("HF_TOKEN")}'}
+
+        try:
+            from huggingface_hub import get_token
+            token = get_token()
+        except ImportError:
+            token = os.getenv("HF_TOKEN")
+
+        if token is not None:
+            self.session.headers = {'authorization': f'Bearer {token}'}

    def sanitize_model_and_branch_names(self, model, branch):
        if model[-1] == '/':
--- a/extensions/coqui_tts/script.py
+++ b/extensions/coqui_tts/script.py
@ -6,6 +6,7 @@ import time
 from pathlib import Path

 import gradio as gr
+import torch
 from TTS.api import TTS
 from TTS.utils.synthesizer import Synthesizer

@ -23,7 +24,7 @@ params = {
    "voice": "female_01.wav",
    "language": "English",
    "model_name": "tts_models/multilingual/multi-dataset/xtts_v2",
-    "device": "cuda"
+    "device": "cuda" if torch.cuda.is_available() else "cpu"
 }

 this_dir = str(Path(__file__).parent.resolve())
--- a/extensions/openai/completions.py
+++ b/extensions/openai/completions.py
@ -110,22 +110,6 @@ def process_parameters(body, is_legacy=False):
    logits_processor = []
    logit_bias = body.get('logit_bias', None)
    if logit_bias:  # {str: float, ...}
-        # XXX convert tokens from tiktoken based on requested model
-        # Ex.: 'logit_bias': {'1129': 100, '11442': 100, '16243': 100}
-        try:
-            encoder = tiktoken.encoding_for_model(generate_params['model'])
-            new_logit_bias = {}
-            for logit, bias in logit_bias.items():
-                for x in encode(encoder.decode([int(logit)]), add_special_tokens=False)[0]:
-                    if int(x) in [0, 1, 2, 29871]:  # XXX LLAMA tokens
-                        continue
-
-                    new_logit_bias[str(int(x))] = bias
-            debug_msg('logit_bias_map', logit_bias, '->', new_logit_bias)
-            logit_bias = new_logit_bias
-        except KeyError:
-            pass  # assume native tokens if we can't find the tokenizer
-
        logits_processor = [LogitsBiasProcessor(logit_bias)]

    logprobs = None  # coming to chat eventually
--- a/grammars/roleplay.gbnf
+++ b/grammars/roleplay.gbnf
@ -0,0 +1,4 @@
+phrasePattern ::= "*" [A-ZÀ-Ü] ( [A-Za-z'.?!,:;-à-üÀ-Ü0-9]+ " " )* [A-Za-z'.?!,:;-à-üÀ-Ü0-9]+ "*"
+quotedText ::= "\"" [A-ZÀ-Ü] [A-Za-z'.*?!,:;-à-üÀ-Ü0-9]* (" " [A-Za-z'.*?!,:;-à-üÀ-Ü0-9]+)* "\""
+root ::= phrasePattern singleSpace quotedText singleSpace phrasePattern singleSpace quotedText singleSpace (phrasePattern singleSpace quotedText singleSpace)?
+singleSpace ::= " "
--- a/modules/ui_parameters.py
+++ b/modules/ui_parameters.py
@ -115,6 +115,6 @@ def get_truncation_length():
 def load_grammar(name):
    p = Path(f'grammars/{name}')
    if p.exists():
-        return open(p, 'r').read()
+        return open(p, 'r', encoding='utf-8').read()
    else:
        return ''
--- a/one_click.py
+++ b/one_click.py
@ -149,17 +149,17 @@ def run_cmd(cmd, assert_success=False, environment=False, capture_output=False,
    if environment:
        if is_windows():
            conda_bat_path = os.path.join(script_dir, "installer_files", "conda", "condabin", "conda.bat")
-            cmd = "\"" + conda_bat_path + "\" activate \"" + conda_env_path + "\" >nul && " + cmd
+            cmd = f'"{conda_bat_path}" activate "{conda_env_path}" >nul && {cmd}'
        else:
            conda_sh_path = os.path.join(script_dir, "installer_files", "conda", "etc", "profile.d", "conda.sh")
-            cmd = ". \"" + conda_sh_path + "\" && conda activate \"" + conda_env_path + "\" && " + cmd
+            cmd = f'. "{conda_sh_path}" && conda activate "{conda_env_path}" && {cmd}'

    # Run shell commands
    result = subprocess.run(cmd, shell=True, capture_output=capture_output, env=env)

    # Assert the command ran successfully
    if assert_success and result.returncode != 0:
-        print("Command '" + cmd + "' failed with exit status code '" + str(result.returncode) + "'.\n\nExiting now.\nTry running the start/update script again.")
+        print(f"Command '{cmd}' failed with exit status code '{str(result.returncode)}'.\n\nExiting now.\nTry running the start/update script again.")
        sys.exit(1)

    return result
@ -257,7 +257,7 @@ def install_webui():

 def update_requirements(initial_installation=False):
    # Create .git directory if missing
-    if not os.path.isdir(os.path.join(script_dir, ".git")):
+    if not os.path.exists(os.path.join(script_dir, ".git")):
        git_creation_cmd = 'git init -b main && git remote add origin https://github.com/oobabooga/text-generation-webui && git fetch && git symbolic-ref refs/remotes/origin/HEAD refs/remotes/origin/main && git reset --hard origin/main && git branch --set-upstream-to=origin/main'
        run_cmd(git_creation_cmd, environment=True, assert_success=True)

@ -291,7 +291,7 @@ def update_requirements(initial_installation=False):
        for i, extension in enumerate(extensions):
            print(f"\n\n--- [{i+1}/{len(extensions)}]: {extension}\n\n")
            extension_req_path = os.path.join("extensions", extension, "requirements.txt")
-            run_cmd("python -m pip install -r " + extension_req_path + " --upgrade", assert_success=False, environment=True)
+            run_cmd(f"python -m pip install -r {extension_req_path} --upgrade", assert_success=False, environment=True)
    elif initial_installation:
        print_big_message("Will not install extensions due to INSTALL_EXTENSIONS environment variable.")

@ -299,7 +299,6 @@ def update_requirements(initial_installation=False):
    torver = torch_version()
    is_cuda = '+cu' in torver
    is_cuda118 = '+cu118' in torver  # 2.1.0+cu118
-    is_cuda117 = '+cu117' in torver  # 2.0.1+cu117
    is_rocm = '+rocm' in torver  # 2.0.1+rocm5.4.2
    is_intel = '+cxx11' in torver  # 2.0.1a0+cxx11.abi
    is_cpu = '+cpu' in torver  # 2.0.1+cpu
@ -320,11 +319,9 @@ def update_requirements(initial_installation=False):

    # Prepare the requirements file
    textgen_requirements = open(requirements_file).read().splitlines()
-    if is_cuda117:
-        textgen_requirements = [req.replace('+cu121', '+cu117').replace('+cu122', '+cu117').replace('torch2.1', 'torch2.0') for req in textgen_requirements]
-    elif is_cuda118:
+    if is_cuda118:
        textgen_requirements = [req.replace('+cu121', '+cu118').replace('+cu122', '+cu118') for req in textgen_requirements]
-    if is_windows() and (is_cuda117 or is_cuda118):  # No flash-attention on Windows for CUDA 11
+    if is_windows() and is_cuda118:  # No flash-attention on Windows for CUDA 11
        textgen_requirements = [req for req in textgen_requirements if 'jllllll/flash-attention' not in req]

    with open('temp_requirements.txt', 'w') as file:
@ -335,13 +332,13 @@ def update_requirements(initial_installation=False):
    for req in git_requirements:
        url = req.replace("git+", "")
        package_name = url.split("/")[-1].split("@")[0].rstrip(".git")
-        run_cmd("python -m pip uninstall -y " + package_name, environment=True)
+        run_cmd(f"python -m pip uninstall -y {package_name}", environment=True)
        print(f"Uninstalled {package_name}")

    # Make sure that API requirements are installed (temporary)
    extension_req_path = os.path.join("extensions", "openai", "requirements.txt")
    if os.path.exists(extension_req_path):
-        run_cmd("python -m pip install -r " + extension_req_path + " --upgrade", environment=True)
+        run_cmd(f"python -m pip install -r {extension_req_path} --upgrade", environment=True)

    # Install/update the project requirements
    run_cmd("python -m pip install -r temp_requirements.txt --upgrade", assert_success=True, environment=True)
--- a/requirements.txt
+++ b/requirements.txt
@ -29,67 +29,39 @@ bitsandbytes==0.41.1; platform_system != "Windows"
 https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows"

 # llama-cpp-python (CPU only, AVX2)
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.36+cpuavx2-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.36+cpuavx2-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.36+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.36+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"

 # llama-cpp-python (CUDA, no tensor cores)
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.31+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.31+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.31+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.31+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.31+cu121-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.31+cu121-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.31+cu121-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.31+cu121-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.36+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.36+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.36+cu121-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.36+cu121-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"

 # llama-cpp-python (CUDA, tensor cores)
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.31+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.31+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.31+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.31+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.31+cu121-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.31+cu121-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.31+cu121-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.31+cu121-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.36+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.36+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.36+cu121-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.36+cu121-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"

 # CUDA wheels
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
 https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
 https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
 https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
 https://github.com/jllllll/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu121torch2.1cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
 https://github.com/jllllll/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu121torch2.1cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/jllllll/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu121torch2.1cxx11abiFALSE-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/jllllll/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu121torch2.1cxx11abiFALSE-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
 https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu122torch2.1cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu122torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu122torch2.1cxx11abiFALSE-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu122torch2.1cxx11abiFALSE-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
 https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
 https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
 https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
 https://github.com/jllllll/ctransformers-cuBLAS-wheels/releases/download/AVX2/ctransformers-0.2.27+cu121-py3-none-any.whl
 autoawq==0.1.8; platform_system == "Linux" or platform_system == "Windows"
--- a/requirements_amd.txt
+++ b/requirements_amd.txt
@ -29,27 +29,17 @@ bitsandbytes==0.38.1; platform_system != "Windows"
 https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.38.1-py3-none-win_amd64.whl; platform_system == "Windows"

 # llama-cpp-python (CPU only, AVX2)
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.36+cpuavx2-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.36+cpuavx2-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.36+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.36+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"

 # AMD wheels
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.31+rocm5.6.1-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.31+rocm5.6.1-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.31+rocm5.6.1-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.31+rocm5.6.1-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.36+rocm5.6.1-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.36+rocm5.6.1-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
 https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
 https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
--- a/requirements_amd_noavx2.txt
+++ b/requirements_amd_noavx2.txt
@ -29,23 +29,15 @@ bitsandbytes==0.38.1; platform_system != "Windows"
 https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.38.1-py3-none-win_amd64.whl; platform_system == "Windows"

 # llama-cpp-python (CPU only, no AVX2)
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.36+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.36+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.36+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.36+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"

 # AMD wheels
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
 https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
 https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
--- a/requirements_apple_intel.txt
+++ b/requirements_apple_intel.txt
@ -29,15 +29,9 @@ bitsandbytes==0.41.1; platform_system != "Windows"
 https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows"

 # Mac wheels
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/metal/llama_cpp_python-0.2.31-cp311-cp311-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/metal/llama_cpp_python-0.2.31-cp310-cp310-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/metal/llama_cpp_python-0.2.31-cp39-cp39-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/metal/llama_cpp_python-0.2.31-cp38-cp38-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.8"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/metal/llama_cpp_python-0.2.31-cp311-cp311-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/metal/llama_cpp_python-0.2.31-cp310-cp310-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/metal/llama_cpp_python-0.2.31-cp39-cp39-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/metal/llama_cpp_python-0.2.31-cp38-cp38-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.8"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/metal/llama_cpp_python-0.2.31-cp311-cp311-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/metal/llama_cpp_python-0.2.31-cp310-cp310-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/metal/llama_cpp_python-0.2.31-cp39-cp39-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/metal/llama_cpp_python-0.2.31-cp38-cp38-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.8"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.36-cp311-cp311-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.36-cp310-cp310-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.10"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.36-cp311-cp311-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.36-cp310-cp310-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.10"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.36-cp311-cp311-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.36-cp310-cp310-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.10"
--- a/requirements_apple_silicon.txt
+++ b/requirements_apple_silicon.txt
@ -29,19 +29,11 @@ bitsandbytes==0.41.1; platform_system != "Windows"
 https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows"

 # Mac wheels
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/metal/llama_cpp_python-0.2.31-cp311-cp311-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/metal/llama_cpp_python-0.2.31-cp310-cp310-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/metal/llama_cpp_python-0.2.31-cp39-cp39-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/metal/llama_cpp_python-0.2.31-cp38-cp38-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.8"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/metal/llama_cpp_python-0.2.31-cp311-cp311-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/metal/llama_cpp_python-0.2.31-cp310-cp310-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/metal/llama_cpp_python-0.2.31-cp39-cp39-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/metal/llama_cpp_python-0.2.31-cp38-cp38-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.8"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/metal/llama_cpp_python-0.2.31-cp311-cp311-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/metal/llama_cpp_python-0.2.31-cp310-cp310-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/metal/llama_cpp_python-0.2.31-cp39-cp39-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/metal/llama_cpp_python-0.2.31-cp38-cp38-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.8"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/metal/llama_cpp_python-0.2.31-cp311-cp311-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/metal/llama_cpp_python-0.2.31-cp310-cp310-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/metal/llama_cpp_python-0.2.31-cp39-cp39-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/metal/llama_cpp_python-0.2.31-cp38-cp38-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.8"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.36-cp311-cp311-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.36-cp310-cp310-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.10"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.36-cp311-cp311-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.36-cp310-cp310-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.10"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.36-cp311-cp311-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.36-cp310-cp310-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.10"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.36-cp311-cp311-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.36-cp310-cp310-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.10"
--- a/requirements_cpu_only.txt
+++ b/requirements_cpu_only.txt
@ -29,11 +29,7 @@ bitsandbytes==0.41.1; platform_system != "Windows"
 https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows"

 # llama-cpp-python (CPU only, AVX2)
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx2-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.36+cpuavx2-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.36+cpuavx2-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.36+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.36+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
--- a/requirements_cpu_only_noavx2.txt
+++ b/requirements_cpu_only_noavx2.txt
@ -29,11 +29,7 @@ bitsandbytes==0.41.1; platform_system != "Windows"
 https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows"

 # llama-cpp-python (CPU only, no AVX2)
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.36+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.36+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.36+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.36+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
--- a/requirements_noavx2.txt
+++ b/requirements_noavx2.txt
@ -29,67 +29,39 @@ bitsandbytes==0.41.1; platform_system != "Windows"
 https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows"

 # llama-cpp-python (CPU only, no AVX2)
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/cpu/llama_cpp_python-0.2.31+cpuavx-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.36+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.36+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.36+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.36+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"

 # llama-cpp-python (CUDA, no tensor cores)
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.31+cu121avx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.31+cu121avx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.31+cu121avx-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.31+cu121avx-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.31+cu121avx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.31+cu121avx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.31+cu121avx-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.31+cu121avx-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.36+cu121avx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.36+cu121avx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.36+cu121avx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.36+cu121avx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"

 # llama-cpp-python (CUDA, tensor cores)
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.31+cu121avx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.31+cu121avx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.31+cu121avx-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.31+cu121avx-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.31+cu121avx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.31+cu121avx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.31+cu121avx-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/oobabooga/llama-cpp-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.31+cu121avx-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.36+cu121avx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.36+cu121avx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.36+cu121avx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.36+cu121avx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"

 # CUDA wheels
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
 https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
 https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
 https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
 https://github.com/jllllll/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu121torch2.1cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
 https://github.com/jllllll/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu121torch2.1cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/jllllll/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu121torch2.1cxx11abiFALSE-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/jllllll/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu121torch2.1cxx11abiFALSE-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
 https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu122torch2.1cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu122torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu122torch2.1cxx11abiFALSE-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu122torch2.1cxx11abiFALSE-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
 https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
 https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
 https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
 https://github.com/jllllll/ctransformers-cuBLAS-wheels/releases/download/AVX/ctransformers-0.2.27+cu121-py3-none-any.whl
 autoawq==0.1.8; platform_system == "Linux" or platform_system == "Windows"