ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Flash Attention whls

Browse source
This commit is contained in:
Daniel Han 2025-05-26 22:48:46 -07:00
commit 0bf5e2be15
2 changed files with 45 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

42
pyproject.toml
View file

@ -550,6 +550,48 @@ cu128-ampere-torch270 = [
"unsloth[flashattention]",
]
flashattentiontorch260abiFALSEcu12x = [
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiFALSE-cp39-cp39-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.9'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiFALSE-cp310-cp310-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.10'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiFALSE-cp311-cp311-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.11'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiFALSE-cp312-cp312-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.12'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiFALSE-cp313-cp313-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.13'",
]
flashattentiontorch260abiTRUEcu12x = [
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiTRUE-cp39-cp39-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.9'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiTRUE-cp310-cp310-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.10'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiTRUE-cp311-cp311-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.11'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiTRUE-cp312-cp312-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.12'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiTRUE-cp313-cp313-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.13'",
]
flashattentiontorch250abiFALSEcu12x = [
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.5cxx11abiFALSE-cp39-cp39-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.9'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.5cxx11abiFALSE-cp310-cp310-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.10'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.5cxx11abiFALSE-cp311-cp311-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.11'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.5cxx11abiFALSE-cp312-cp312-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.12'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.5cxx11abiFALSE-cp313-cp313-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.13'",
]
flashattentiontorch250abiTRUEcu12x = [
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.5cxx11abiTRUE-cp39-cp39-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.9'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.5cxx11abiTRUE-cp310-cp310-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.10'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.5cxx11abiTRUE-cp311-cp311-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.11'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.5cxx11abiTRUE-cp312-cp312-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.12'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.5cxx11abiTRUE-cp313-cp313-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.13'",
]
flashattentiontorch240abiFALSEcu12x = [
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.4cxx11abiFALSE-cp39-cp39-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.9'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.4cxx11abiFALSE-cp310-cp310-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.10'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.4cxx11abiFALSE-cp311-cp311-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.11'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.4cxx11abiFALSE-cp312-cp312-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.12'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.4cxx11abiFALSE-cp313-cp313-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.13'",
]
flashattentiontorch240abiTRUEcu12x = [
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.4cxx11abiTRUE-cp39-cp39-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.9'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.4cxx11abiTRUE-cp310-cp310-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.10'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.4cxx11abiTRUE-cp311-cp311-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.11'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.4cxx11abiTRUE-cp312-cp312-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.12'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.4cxx11abiTRUE-cp313-cp313-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.13'",
]
intel-gpu-torch260 = [
"unsloth[huggingface]",

4
unsloth/_auto_install.py
View file

@ -18,7 +18,9 @@ from packaging.version import Version as V
v = V(torch.__version__)
cuda = str(torch.version.cuda)
is_ampere = torch.cuda.get_device_capability()[0] >= 8
if cuda != "12.1" and cuda != "11.8" and cuda != "12.4" and cuda != "12.6" and cuda != "12.8": raise RuntimeError(f"CUDA = {cuda} not supported!")
USE_ABI = torch._C._GLIBCXX_USE_CXX11_ABI
if cuda not in ("11.8", "12.1", "12.4", "12.6", "12.8"):
raise RuntimeError(f"CUDA = {cuda} not supported!")
if v <= V('2.1.0'): raise RuntimeError(f"Torch = {v} too old!")
elif v <= V('2.1.1'): x = 'cu{}{}-torch211'
elif v <= V('2.1.2'): x = 'cu{}{}-torch212'