From 78f5d2ea8e9d21fa46d29037fc768c639d17722f Mon Sep 17 00:00:00 2001
From: dan_the_3rd <43445237+danthe3rd@users.noreply.github.com>
Date: Thu, 14 Mar 2024 12:36:00 +0000
Subject: [PATCH] Prepare release 0.0.25 (fairinternal/xformers#1058)

* Prepare release 0.0.25

* Add note about supported PT version for binaries

__original_commit__ = fairinternal/xformers@0510e145c8d950cffd31b47e47e36b0f6ef1e664
---
 .github/workflows/conda.yml  |  4 ++--
 .github/workflows/wheels.yml |  8 ++++----
 CHANGELOG.md                 | 12 +++++++++---
 version.txt                  |  2 +-
 4 files changed, 16 insertions(+), 10 deletions(-)

diff --git a/.github/workflows/conda.yml b/.github/workflows/conda.yml
index 42647802d2..577273c527 100644
--- a/.github/workflows/conda.yml
+++ b/.github/workflows/conda.yml
@@ -33,13 +33,13 @@ jobs:
           - "3.9"
           - "3.10"
         config:
-          - torch_version: "2.2.0"
+          - torch_version: "2.2.1"
             torch_channel: "pytorch"
             cuda_version: "12.1.0"
             cuda_dep_runtime: ">=12.0,<13.0"
             cuda_short_version: "121"
 
-          - torch_version: "2.2.0"
+          - torch_version: "2.2.1"
             torch_channel: "pytorch"
             cuda_version: "11.8.0"
             cuda_dep_runtime: ">=11.7,<11.9"
diff --git a/.github/workflows/wheels.yml b/.github/workflows/wheels.yml
index 93d0889315..1a91c86064 100644
--- a/.github/workflows/wheels.yml
+++ b/.github/workflows/wheels.yml
@@ -27,7 +27,7 @@ jobs:
           - "3.10"
           - "3.11"
         torch_version:
-          - "2.2.0"
+          - "2.2.1"
         cuda_short_version:
           - "118"
           - "121"
@@ -45,7 +45,7 @@ jobs:
     uses: ./.github/workflows/wheels_upload_pip.yml
     with:
       twine_username: __token__
-      filter: "*torch2.2.0+cu121*"
+      filter: "*torch2.2.1+cu121*"
       execute: ${{ github.repository == 'facebookresearch/xformers' && github.event_name != 'pull_request' }}
     secrets:
       twine_password: ${{ secrets.PYPI_TOKEN }}
@@ -57,7 +57,7 @@ jobs:
       aws_role: "arn:aws:iam::749337293305:role/pytorch_bot_uploader_role"
       s3_path: s3://pytorch/whl/cu118/
       aws_s3_cp_extra_args: --acl public-read
-      filter: "*torch2.2.0+cu118*"
+      filter: "*torch2.2.1+cu118*"
       execute: ${{ github.repository == 'facebookresearch/xformers' && github.ref_type == 'tag' }}
 
   upload_pt_cu121:
@@ -67,6 +67,6 @@ jobs:
       aws_role: "arn:aws:iam::749337293305:role/pytorch_bot_uploader_role"
       s3_path: s3://pytorch/whl/cu121/
       aws_s3_cp_extra_args: --acl public-read
-      filter: "*torch2.2.0+cu121*"
+      filter: "*torch2.2.1+cu121*"
       execute: ${{ github.repository == 'facebookresearch/xformers' && github.ref_type == 'tag' }}
 
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 62e6a1e445..669f2f1f68 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -4,9 +4,15 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [0.0.25] - TBD
+## [0.0.26] - TBD
 ### Added
-- New merge_attentions function
+### Improved
+### Removed
+
+## [0.0.25] - 2024-03-14
+Pre-built binary wheels require PyTorch 2.2.1
+### Added
+- New `merge_attentions` function
 ### Improved
 - fMHA: Updated Flash-Attention to v2.5.6: this has a performance improvement for multiquery.
 - fMHA: triton_splitk changed and expanded. Now amalgamates using LSE. Can autotune, supports causal with a small number of queries - not just 1. Experimental support for paged attention.
@@ -18,7 +24,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ## [0.0.24] - 2024-01-31
 Pre-built binary wheels require PyTorch 2.2.0
 ### Added
-- Added components for model/sequence parallelism, as near-drop-in replacements for FairScale/Megatron Column&RowParallelLinear modules. They support fusing communication and computation for sequence parallelism, thus making the communication effectively free.
+- Added components for model/sequence parallelism, as near-drop-in replacements for FairScale/Megatron Column&RowParallelLinear modules. They support fusing communication and computation for sequence parallelism, thus making the communication effectively free. [Read more](https://twitter.com/d_haziza/status/1753030654118211593)
 - Added kernels for training models with 2:4-sparsity. We introduced a very fast kernel for converting a matrix A into 24-sparse format, which can be used during training to sparsify weights dynamically, activations etc... xFormers also provides an API that is compatible with torch-compile, see `xformers.ops.sparsify24`.
 ### Improved
 - Make selective activation checkpointing be compatible with torch.compile.
diff --git a/version.txt b/version.txt
index 2678ff8d63..c4475d3bb7 100644
--- a/version.txt
+++ b/version.txt
@@ -1 +1 @@
-0.0.25
+0.0.26