Commit f638e65c authored by Woosuk Kwon's avatar Woosuk Kwon
Browse files

Upgrade to v2.5.8.post1

parent 422545b4
...@@ -43,35 +43,14 @@ jobs: ...@@ -43,35 +43,14 @@ jobs:
# Using ubuntu-20.04 instead of 22.04 for more compatibility (glibc). Ideally we'd use the # Using ubuntu-20.04 instead of 22.04 for more compatibility (glibc). Ideally we'd use the
# manylinux docker image, but I haven't figured out how to install CUDA on manylinux. # manylinux docker image, but I haven't figured out how to install CUDA on manylinux.
os: [ubuntu-20.04] os: [ubuntu-20.04]
python-version: ['3.7', '3.8', '3.9', '3.10', '3.11'] python-version: ['3.8', '3.9', '3.10', '3.11']
torch-version: ['1.12.1', '1.13.1', '2.0.1', '2.1.2', '2.2.0', '2.3.0.dev20240207'] torch-version: ['2.3.0']
cuda-version: ['11.8.0', '12.2.2'] cuda-version: ['11.8.0', '12.1.1']
# We need separate wheels that either uses C++11 ABI (-D_GLIBCXX_USE_CXX11_ABI) or not. # We need separate wheels that either uses C++11 ABI (-D_GLIBCXX_USE_CXX11_ABI) or not.
# Pytorch wheels currently don't use it, but nvcr images have Pytorch compiled with C++11 ABI. # Pytorch wheels currently don't use it, but nvcr images have Pytorch compiled with C++11 ABI.
# Without this we get import error (undefined symbol: _ZN3c105ErrorC2ENS_14SourceLocationESs) # Without this we get import error (undefined symbol: _ZN3c105ErrorC2ENS_14SourceLocationESs)
# when building without C++11 ABI and using it on nvcr images. # when building without C++11 ABI and using it on nvcr images.
cxx11_abi: ['FALSE', 'TRUE'] cxx11_abi: ['FALSE', 'TRUE']
exclude:
# see https://github.com/pytorch/pytorch/blob/main/RELEASE.md#release-compatibility-matrix
# Pytorch <= 1.12 does not support Python 3.11
- torch-version: '1.12.1'
python-version: '3.11'
# Pytorch >= 2.0 only supports Python >= 3.8
- torch-version: '2.0.1'
python-version: '3.7'
- torch-version: '2.1.2'
python-version: '3.7'
- torch-version: '2.2.0'
python-version: '3.7'
- torch-version: '2.3.0.dev20240207'
python-version: '3.7'
# Pytorch <= 2.0 only supports CUDA <= 11.8
- torch-version: '1.12.1'
cuda-version: '12.2.2'
- torch-version: '1.13.1'
cuda-version: '12.2.2'
- torch-version: '2.0.1'
cuda-version: '12.2.2'
steps: steps:
- name: Checkout - name: Checkout
......
__version__ = "2.5.8" __version__ = "2.5.8.post1"
from vllm_flash_attn.flash_attn_interface import ( from vllm_flash_attn.flash_attn_interface import (
flash_attn_func, flash_attn_func,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment