oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2025-12-06 07:12:10 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge pull request #7296 from oobabooga/dev

Browse source 
Merge dev branch
This commit is contained in:
oobabooga 2025-11-06 00:38:25 -03:00 committed by GitHub
parent fc67e5e692 e7534a90d8
commit 9ad9afad7d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
21 changed files with 64 additions and 55 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

13
.github/workflows/build-portable-release-cuda.yml vendored
View file

@ -60,7 +60,7 @@ jobs:
'os' = @('ubuntu-22.04', 'windows-2022')
'pyver' = @("3.11")
'avx' = @("AVX2")
'cuda' = @("11.7", "12.4")
'cuda' = @("12.4")
}
if ($env:CONFIGIN -ne 'Default') {$env:CONFIGIN.split(';').foreach({$matrix[$_.split(':')[0]] = $_.split(':')[1].split(',')})}
@ -147,22 +147,13 @@ jobs:
# Create CUDA-specific requirements file if needed
cd "text-generation-webui-${VERSION_CLEAN}"
if [[ "$CUDA_VERSION" == "11.7" ]]; then
echo "Creating CUDA 11.7 specific requirements file"
sed 's/cu124/cu117/g' "$BASE_REQ_FILE" > requirements_cuda_temp.txt
REQ_FILE="requirements_cuda_temp.txt"
else
REQ_FILE="$BASE_REQ_FILE"
fi
REQ_FILE="$BASE_REQ_FILE"
# 4. Install packages
echo "Installing Python packages from $REQ_FILE..."
$PIP_PATH install --target="./$PACKAGES_PATH" -r "$REQ_FILE"
# 5. Clean up
if [[ "$CUDA_VERSION" == "11.7" ]]; then
rm requirements_cuda_temp.txt
fi
rm -rf .git cmd* update_wizard* Colab-TextGen-GPU.ipynb docker setup.cfg .github .gitignore requirements/ one_click.py
# 6. Create ZIP file

2
extensions/Training_PRO/script.py
View file

@ -823,7 +823,7 @@ def do_train(lora_name: str, always_override: bool, save_steps: int, micro_batch
lora_model = get_peft_model(shared.model, config)
if not always_override and Path(f"{lora_file_path}/adapter_model.bin").is_file():
logger.info("Loading existing LoRA data...")
state_dict_peft = torch.load(f"{lora_file_path}/adapter_model.bin")
state_dict_peft = torch.load(f"{lora_file_path}/adapter_model.bin", weights_only=True)
set_peft_model_state_dict(lora_model, state_dict_peft)
print(f" + Continue Training on {RED}{lora_file_path}/adapter_model.bin{RESET}")

4
modules/training.py
View file

@ -611,7 +611,7 @@ def do_train(lora_name: str, always_override: bool, q_proj_en: bool, v_proj_en:
bf16=shared.args.bf16,
optim=optimizer,
logging_steps=2 if stop_at_loss > 0 else 5,
evaluation_strategy="steps" if eval_data is not None else "no",
eval_strategy="steps" if eval_data is not None else "no",
eval_steps=math.ceil(eval_steps / gradient_accumulation_steps) if eval_data is not None else None,
save_strategy="steps" if eval_data is not None else "no",
output_dir=lora_file_path,
@ -620,7 +620,7 @@ def do_train(lora_name: str, always_override: bool, q_proj_en: bool, v_proj_en:
# TODO: Enable multi-device support
ddp_find_unused_parameters=None,
no_cuda=shared.args.cpu,
use_ipex=True if is_torch_xpu_available() and not shared.args.cpu else False
# use_ipex=True if is_torch_xpu_available() and not shared.args.cpu else False
),
data_collator=transformers.DataCollatorForLanguageModeling(shared.tokenizer, mlm=False),
callbacks=list([Callbacks()])

11
requirements/full/requirements.txt
View file

@ -5,8 +5,9 @@ colorama
datasets
einops
fastapi==0.112.4
flash-linear-attention==0.3.2
flash-linear-attention==0.4.0
html2text==2025.4.15
huggingface-hub==0.36.0
jinja2==3.1.6
markdown
numpy==2.2.*
@ -39,10 +40,10 @@ sse-starlette==1.6.5
tiktoken
# CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.11/exllamav3-0.0.11+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.11/exllamav3-0.0.11+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.12/exllamav3-0.0.12+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.12/exllamav3-0.0.12+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"

5
requirements/full/requirements_amd.txt
View file

@ -5,6 +5,7 @@ datasets
einops
fastapi==0.112.4
html2text==2025.4.15
huggingface-hub==0.36.0
jinja2==3.1.6
markdown
numpy==2.2.*
@ -37,7 +38,7 @@ sse-starlette==1.6.5
tiktoken
# AMD wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+rocm6.2.4.torch2.6.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"

5
requirements/full/requirements_amd_noavx2.txt
View file

@ -5,6 +5,7 @@ datasets
einops
fastapi==0.112.4
html2text==2025.4.15
huggingface-hub==0.36.0
jinja2==3.1.6
markdown
numpy==2.2.*
@ -37,7 +38,7 @@ sse-starlette==1.6.5
tiktoken
# AMD wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+rocm6.2.4.torch2.6.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"

5
requirements/full/requirements_apple_intel.txt
View file

@ -5,6 +5,7 @@ datasets
einops
fastapi==0.112.4
html2text==2025.4.15
huggingface-hub==0.36.0
jinja2==3.1.6
markdown
numpy==2.2.*
@ -37,5 +38,5 @@ sse-starlette==1.6.5
tiktoken
# Mac wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0-py3-none-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-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0-py3-none-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"

7
requirements/full/requirements_apple_silicon.txt
View file

@ -5,6 +5,7 @@ datasets
einops
fastapi==0.112.4
html2text==2025.4.15
huggingface-hub==0.36.0
jinja2==3.1.6
markdown
numpy==2.2.*
@ -37,6 +38,6 @@ sse-starlette==1.6.5
tiktoken
# Mac wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0-py3-none-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-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0-py3-none-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-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0-py3-none-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-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0-py3-none-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"

5
requirements/full/requirements_cpu_only.txt
View file

@ -5,6 +5,7 @@ datasets
einops
fastapi==0.112.4
html2text==2025.4.15
huggingface-hub==0.36.0
jinja2==3.1.6
markdown
numpy==2.2.*
@ -37,5 +38,5 @@ sse-starlette==1.6.5
tiktoken
# llama.cpp (CPU only, AVX2)
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"

5
requirements/full/requirements_cpu_only_noavx2.txt
View file

@ -5,6 +5,7 @@ datasets
einops
fastapi==0.112.4
html2text==2025.4.15
huggingface-hub==0.36.0
jinja2==3.1.6
markdown
numpy==2.2.*
@ -37,5 +38,5 @@ sse-starlette==1.6.5
tiktoken
# llama.cpp (CPU only, no AVX2)
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"

11
requirements/full/requirements_noavx2.txt
View file

@ -5,8 +5,9 @@ colorama
datasets
einops
fastapi==0.112.4
flash-linear-attention==0.3.2
flash-linear-attention==0.4.0
html2text==2025.4.15
huggingface-hub==0.36.0
jinja2==3.1.6
markdown
numpy==2.2.*
@ -39,10 +40,10 @@ sse-starlette==1.6.5
tiktoken
# CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.11/exllamav3-0.0.11+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.11/exllamav3-0.0.11+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.12/exllamav3-0.0.12+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.12/exllamav3-0.0.12+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"

1
requirements/full/requirements_nowheels.txt
View file

@ -5,6 +5,7 @@ datasets
einops
fastapi==0.112.4
html2text==2025.4.15
huggingface-hub==0.36.0
jinja2==3.1.6
markdown
numpy==2.2.*

5
requirements/portable/requirements.txt
View file

@ -1,6 +1,7 @@
audioop-lts<1.0; python_version >= "3.13"
fastapi==0.112.4
html2text==2025.4.15
huggingface-hub==0.36.0
jinja2==3.1.6
markdown
numpy==2.2.*
@ -22,5 +23,5 @@ sse-starlette==1.6.5
tiktoken
# CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

7
requirements/portable/requirements_apple_intel.txt
View file

@ -1,6 +1,7 @@
audioop-lts<1.0; python_version >= "3.13"
fastapi==0.112.4
html2text==2025.4.15
huggingface-hub==0.36.0
jinja2==3.1.6
markdown
numpy==2.2.*
@ -22,6 +23,6 @@ sse-starlette==1.6.5
tiktoken
# Mac wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0-py3-none-macosx_13_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0-py3-none-macosx_13_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0"

7
requirements/portable/requirements_apple_silicon.txt
View file

@ -1,6 +1,7 @@
audioop-lts<1.0; python_version >= "3.13"
fastapi==0.112.4
html2text==2025.4.15
huggingface-hub==0.36.0
jinja2==3.1.6
markdown
numpy==2.2.*
@ -22,6 +23,6 @@ sse-starlette==1.6.5
tiktoken
# Mac wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0-py3-none-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0-py3-none-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0"

5
requirements/portable/requirements_cpu_only.txt
View file

@ -1,6 +1,7 @@
audioop-lts<1.0; python_version >= "3.13"
fastapi==0.112.4
html2text==2025.4.15
huggingface-hub==0.36.0
jinja2==3.1.6
markdown
numpy==2.2.*
@ -22,5 +23,5 @@ sse-starlette==1.6.5
tiktoken
# llama.cpp (CPU only, AVX2)
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"

5
requirements/portable/requirements_cpu_only_noavx2.txt
View file

@ -1,6 +1,7 @@
audioop-lts<1.0; python_version >= "3.13"
fastapi==0.112.4
html2text==2025.4.15
huggingface-hub==0.36.0
jinja2==3.1.6
markdown
numpy==2.2.*
@ -22,5 +23,5 @@ sse-starlette==1.6.5
tiktoken
# llama.cpp (CPU only, no AVX2)
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"

5
requirements/portable/requirements_noavx2.txt
View file

@ -1,6 +1,7 @@
audioop-lts<1.0; python_version >= "3.13"
fastapi==0.112.4
html2text==2025.4.15
huggingface-hub==0.36.0
jinja2==3.1.6
markdown
numpy==2.2.*
@ -22,5 +23,5 @@ sse-starlette==1.6.5
tiktoken
# CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

1
requirements/portable/requirements_nowheels.txt
View file

@ -1,6 +1,7 @@
audioop-lts<1.0; python_version >= "3.13"
fastapi==0.112.4
html2text==2025.4.15
huggingface-hub==0.36.0
jinja2==3.1.6
markdown
numpy==2.2.*

5
requirements/portable/requirements_vulkan.txt
View file

@ -1,6 +1,7 @@
audioop-lts<1.0; python_version >= "3.13"
fastapi==0.112.4
html2text==2025.4.15
huggingface-hub==0.36.0
jinja2==3.1.6
markdown
numpy==2.2.*
@ -22,5 +23,5 @@ sse-starlette==1.6.5
tiktoken
# CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

5
requirements/portable/requirements_vulkan_noavx2.txt
View file

@ -1,6 +1,7 @@
audioop-lts<1.0; python_version >= "3.13"
fastapi==0.112.4
html2text==2025.4.15
huggingface-hub==0.36.0
jinja2==3.1.6
markdown
numpy==2.2.*
@ -22,5 +23,5 @@ sse-starlette==1.6.5
tiktoken
# CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"