Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-11-23 00:18:20 +01:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #5655 from oobabooga/dev

Browse Source 
Merge dev branch
This commit is contained in:
oobabooga 2024-03-07 13:13:10 -03:00 committed by GitHub
commit aa0da07af0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
17 changed files with 41 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@ -48,7 +48,7 @@ If you ever need to install something manually in the `installer_files` environm
* There is no need to run any of those scripts (`start_`, `update_wizard_`, or `cmd_`) as admin/root.
* To install the requirements for extensions, you can use the `extensions_reqs` script for your OS. At the end, this script will install the main requirements for the project to make sure that they take precedence in case of version conflicts.
* For additional instructions about AMD and WSL setup, consult [the documentation](https://github.com/oobabooga/text-generation-webui/wiki).
* For automated installation, you can use the `GPU_CHOICE`, `USE_CUDA118`, and `LAUNCH_AFTER_INSTALL` environment variables. For instance: `GPU_CHOICE=A USE_CUDA118=FALSE LAUNCH_AFTER_INSTALL=FALSE ./start_linux.sh`.
* For automated installation, you can use the `GPU_CHOICE`, `USE_CUDA118`, `LAUNCH_AFTER_INSTALL`, and `INSTALL_EXTENSIONS` environment variables. For instance: `GPU_CHOICE=A USE_CUDA118=FALSE LAUNCH_AFTER_INSTALL=FALSE INSTALL_EXTENSIONS=TRUE ./start_linux.sh`.
### Manual installation using Conda
@ -279,6 +279,7 @@ List of command-line flags
|`--cfg-cache` | ExLlamav2_HF: Create an additional cache for CFG negative prompts. Necessary to use CFG with that loader. |
|`--no_flash_attn` | Force flash-attention to not be used. |
|`--cache_8bit` | Use 8-bit cache to save VRAM. |
|`--cache_4bit` | Use Q4 cache to save VRAM. |
|`--num_experts_per_token NUM_EXPERTS_PER_TOKEN` | Number of experts to use for generation. Applies to MoE models like Mixtral. |
#### AutoGPTQ

2
docker/amd/Dockerfile
View File

@ -13,7 +13,7 @@ RUN --mount=type=cache,target=/var/cache/apt,sharing=locked,rw \
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 ./start_linux.sh --verbose
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

2
docker/cpu/Dockerfile
View File

@ -17,7 +17,7 @@ RUN --mount=type=cache,target=/var/cache/apt,sharing=locked,rw \
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 ./start_linux.sh --verbose
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

2
docker/intel/Dockerfile
View File

@ -13,7 +13,7 @@ RUN --mount=type=cache,target=/var/cache/apt,sharing=locked,rw \
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 ./start_linux.sh --verbose
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

2
docker/nvidia/Dockerfile
View File

@ -13,7 +13,7 @@ RUN --mount=type=cache,target=/var/cache/apt,sharing=locked,rw \
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 ./start_linux.sh --verbose
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

1
docs/04 - Model Tab.md
View File

@ -46,6 +46,7 @@ Examples:
* **cfg-cache**: Creates a second cache to hold the CFG negative prompts. You need to set this if and only if you intend to use CFG in the "Parameters" > "Generation" tab. Checking this parameter doubles the cache VRAM usage.
* **no_flash_attn**: Disables flash attention. Otherwise, it is automatically used as long as the library is installed.
* **cache_8bit**: Create a 8-bit precision cache instead of a 16-bit one. This saves VRAM but increases perplexity (I don't know by how much).
* **cache_4bit**: Creates a Q4 cache using grouped quantization.
### ExLlamav2

3
modules/exllamav2.py
View File

@ -6,6 +6,7 @@ from exllamav2 import (
ExLlamaV2,
ExLlamaV2Cache,
ExLlamaV2Cache_8bit,
ExLlamaV2Cache_Q4,
ExLlamaV2Config,
ExLlamaV2Tokenizer
)
@ -60,6 +61,8 @@ class Exllamav2Model:
if shared.args.cache_8bit:
cache = ExLlamaV2Cache_8bit(model, lazy=shared.args.autosplit)
elif shared.args.cache_4bit:
cache = ExLlamaV2Cache_Q4(model, lazy=shared.args.autosplit)
else:
cache = ExLlamaV2Cache(model, lazy=shared.args.autosplit)

5
modules/exllamav2_hf.py
View File

@ -8,6 +8,7 @@ from exllamav2 import (
ExLlamaV2,
ExLlamaV2Cache,
ExLlamaV2Cache_8bit,
ExLlamaV2Cache_Q4,
ExLlamaV2Config
)
from torch.nn import CrossEntropyLoss
@ -50,6 +51,8 @@ class Exllamav2HF(PreTrainedModel):
if shared.args.cache_8bit:
self.ex_cache = ExLlamaV2Cache_8bit(self.ex_model, lazy=shared.args.autosplit)
elif shared.args.cache_4bit:
self.ex_cache = ExLlamaV2Cache_Q4(self.ex_model, lazy=shared.args.autosplit)
else:
self.ex_cache = ExLlamaV2Cache(self.ex_model, lazy=shared.args.autosplit)
@ -60,6 +63,8 @@ class Exllamav2HF(PreTrainedModel):
if shared.args.cfg_cache:
if shared.args.cache_8bit:
self.ex_cache_negative = ExLlamaV2Cache_8bit(self.ex_model)
elif shared.args.cache_4bit:
self.ex_cache_negative = ExLlamaV2Cache_Q4(self.ex_model)
else:
self.ex_cache_negative = ExLlamaV2Cache(self.ex_model)

2
modules/loaders.py
View File

@ -78,6 +78,7 @@ loaders_and_params = OrderedDict({
'no_flash_attn',
'num_experts_per_token',
'cache_8bit',
'cache_4bit',
'autosplit',
'alpha_value',
'compress_pos_emb',
@ -90,6 +91,7 @@ loaders_and_params = OrderedDict({
'no_flash_attn',
'num_experts_per_token',
'cache_8bit',
'cache_4bit',
'autosplit',
'alpha_value',
'compress_pos_emb',

1
modules/shared.py
View File

@ -139,6 +139,7 @@ group.add_argument('--max_seq_len', type=int, default=2048, help='Maximum sequen
group.add_argument('--cfg-cache', action='store_true', help='ExLlamav2_HF: Create an additional cache for CFG negative prompts. Necessary to use CFG with that loader.')
group.add_argument('--no_flash_attn', action='store_true', help='Force flash-attention to not be used.')
group.add_argument('--cache_8bit', action='store_true', help='Use 8-bit cache to save VRAM.')
group.add_argument('--cache_4bit', action='store_true', help='Use Q4 cache to save VRAM.')
group.add_argument('--num_experts_per_token', type=int, default=2, help='Number of experts to use for generation. Applies to MoE models like Mixtral.')
# AutoGPTQ

1
modules/ui.py
View File

@ -76,6 +76,7 @@ def list_model_elements():
'no_flash_attn',
'num_experts_per_token',
'cache_8bit',
'cache_4bit',
'autosplit',
'threads',
'threads_batch',

1
modules/ui_model_menu.py
View File

@ -132,6 +132,7 @@ def create_ui():
shared.gradio['disk'] = gr.Checkbox(label="disk", value=shared.args.disk)
shared.gradio['bf16'] = gr.Checkbox(label="bf16", value=shared.args.bf16)
shared.gradio['cache_8bit'] = gr.Checkbox(label="cache_8bit", value=shared.args.cache_8bit, info='Use 8-bit cache to save VRAM.')
shared.gradio['cache_4bit'] = gr.Checkbox(label="cache_4bit", value=shared.args.cache_4bit, info='Use Q4 cache to save VRAM.')
shared.gradio['autosplit'] = gr.Checkbox(label="autosplit", value=shared.args.autosplit, info='Automatically split the model tensors across the available GPUs.')
shared.gradio['no_flash_attn'] = gr.Checkbox(label="no_flash_attn", value=shared.args.no_flash_attn, info='Force flash-attention to not be used.')
shared.gradio['cfg_cache'] = gr.Checkbox(label="cfg-cache", value=shared.args.cfg_cache, info='Necessary to use CFG with this loader.')

7
one_click.py
View File

@ -342,7 +342,7 @@ def update_requirements(initial_installation=False, pull=True):
files_to_check = [
'start_linux.sh', 'start_macos.sh', 'start_windows.bat', 'start_wsl.bat',
'update_linux.sh', 'update_macos.sh', 'update_windows.bat', 'update_wsl.bat',
'update_wizard_linux.sh', 'update_wizard_macos.sh', 'update_wizard_windows.bat', 'update_wizard_wsl.bat',
'one_click.py'
]
@ -356,6 +356,9 @@ def update_requirements(initial_installation=False, pull=True):
print_big_message(f"File '{file_name}' was updated during 'git pull'. Please run the script again.")
exit(1)
if os.environ.get("INSTALL_EXTENSIONS", "").lower() in ("yes", "y", "true", "1", "t", "on"):
install_extensions_requirements()
# Update PyTorch
if not initial_installation:
update_pytorch()
@ -387,7 +390,7 @@ def update_requirements(initial_installation=False, pull=True):
if is_cuda118:
textgen_requirements = [req.replace('+cu121', '+cu118').replace('+cu122', '+cu118') for req in textgen_requirements]
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]
textgen_requirements = [req for req in textgen_requirements if 'oobabooga/flash-attention' not in req]
with open('temp_requirements.txt', 'w') as file:
file.write('\n'.join(textgen_requirements))

10
requirements.txt
View File

@ -56,11 +56,11 @@ https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu1
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-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/oobabooga/exllamav2/releases/download/v0.0.14.1/exllamav2-0.0.14.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.14.1/exllamav2-0.0.14.1+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.14.1/exllamav2-0.0.14.1+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.14.1/exllamav2-0.0.14.1+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.14.1/exllamav2-0.0.14.1-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.15/exllamav2-0.0.15+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.15/exllamav2-0.0.15+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.15/exllamav2-0.0.15+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.15/exllamav2-0.0.15+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.15/exllamav2-0.0.15-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"
https://github.com/oobabooga/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2.0cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2.0cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"

6
requirements_amd.txt
View File

@ -40,8 +40,8 @@ https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/ro
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.55+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/oobabooga/exllamav2/releases/download/v0.0.14.1/exllamav2-0.0.14.1+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.14.1/exllamav2-0.0.14.1+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.14.1/exllamav2-0.0.14.1-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.15/exllamav2-0.0.15+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.15/exllamav2-0.0.15+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.15/exllamav2-0.0.15-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
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"

6
requirements_amd_noavx2.txt
View File

@ -38,8 +38,8 @@ https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cp
# 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/oobabooga/exllamav2/releases/download/v0.0.14.1/exllamav2-0.0.14.1+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.14.1/exllamav2-0.0.14.1+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.14.1/exllamav2-0.0.14.1-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.15/exllamav2-0.0.15+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.15/exllamav2-0.0.15+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.15/exllamav2-0.0.15-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
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"

10
requirements_noavx2.txt
View File

@ -56,11 +56,11 @@ https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu1
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-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/oobabooga/exllamav2/releases/download/v0.0.14.1/exllamav2-0.0.14.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.14.1/exllamav2-0.0.14.1+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.14.1/exllamav2-0.0.14.1+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.14.1/exllamav2-0.0.14.1+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.14.1/exllamav2-0.0.14.1-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.15/exllamav2-0.0.15+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.15/exllamav2-0.0.15+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.15/exllamav2-0.0.15+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.15/exllamav2-0.0.15+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.15/exllamav2-0.0.15-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"
https://github.com/oobabooga/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2.0cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2.0cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"