From f638e65ce18d77254f7fa30b9c16e0ec90e14ae3 Mon Sep 17 00:00:00 2001
From: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Date: Tue, 7 May 2024 00:25:26 +0000
Subject: [PATCH] Upgrade to v2.5.8.post1

---
 .github/workflows/publish.yml | 27 +++------------------------
 vllm_flash_attn/__init__.py   |  2 +-
 2 files changed, 4 insertions(+), 25 deletions(-)

diff --git a/.github/workflows/publish.yml b/.github/workflows/publish.yml
index 2413d3e96..c3a5c659d 100644
--- a/.github/workflows/publish.yml
+++ b/.github/workflows/publish.yml
@@ -43,35 +43,14 @@ jobs:
           # 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.
           os: [ubuntu-20.04]
-          python-version: ['3.7', '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']
-          cuda-version: ['11.8.0', '12.2.2']
+          python-version: ['3.8', '3.9', '3.10', '3.11']
+          torch-version: ['2.3.0']
+          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.
           # 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)
           # when building without C++11 ABI and using it on nvcr images.
           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:
       - name: Checkout
diff --git a/vllm_flash_attn/__init__.py b/vllm_flash_attn/__init__.py
index 14dc0f392..ca802d0e2 100644
--- a/vllm_flash_attn/__init__.py
+++ b/vllm_flash_attn/__init__.py
@@ -1,4 +1,4 @@
-__version__ = "2.5.8"
+__version__ = "2.5.8.post1"
 
 from vllm_flash_attn.flash_attn_interface import (
     flash_attn_func,