drisspg 3ecfe6be25 [Submodule] Turning flash-attention integration into 3rd party submod (#144120) (#146372) ... Summary: # Summary ### Sticky points Cuda-graph rng handling has changed / deviated from original implementation. We will be left with a dangling 'offset' val and confusing naming due to BC ## Dependencies - Flash PR: https://github.com/Dao-AILab/flash-attention/pull/1419 ### Other Points - The BC linter is complaining about losing generate.py and its functions which is not real BC surface cc albanD imported-using-ghimport Test Plan: Imported from OSS Building in dev `buck build @//mode/dev-nosan -c fbcode.nvcc_arch=h100a //caffe2:ATen-cu --show-full-output ` I and Nming the .so I do see that the flash symbols are correctly named: ``` 0000000001c3dfb0 t pytorch_flash::run_mha_bwd(pytorch_flash::Flash_bwd_params&, CUstream_st*)::$_0::operator()() const::{lambda()#1}::operator()() const::{lambda()#1}::operator()() const::{lambda()#7}::operator()() const 0000000001c36080 t pytorch_flash::run_mha_fwd(pytorch_flash::Flash_fwd_params&, CUstream_st*, bool)::$_0::operator()() const::{lambda()#2}::operator()() const::{lambda()#1}::operator()() const::{lambda()#6}::operator()() const 0000000001c360e0 t pytorch_flash::run_mha_fwd(pytorch_flash::Flash_fwd_params&, CUstream_st*, bool)::$_0::operator()() const::{lambda()#2}::operator()() const::{lambda()#1}::operator()() const::{lambda()#7}::operator()() const 0000000001c35fc0 t pytorch_flash::run_mha_fwd(pytorch_flash::Flash_fwd_params&, CUstream_st*, bool)::$_0::operator()() const::{lambda()#1}::operator()() const::{lambda()#1}::operator()() const::{lambda()#6}::operator()() const 0000000001c36020 t pytorch_flash::run_mha_fwd(pytorch_flash::Flash_fwd_params&, CUstream_st*, bool)::$_0::operator()() const::{lambda()#1}::operator()() const::{lambda()#1}::operator()() const::{lambda()#7}::operator()() const ``` Reviewed By: vkuzo Differential Revision: D68502879 Pulled By: drisspg Pull Request resolved: https://github.com/pytorch/pytorch/pull/146372 Approved by: https://github.com/jbschlosser		2025-02-26 00:10:59 +00:00
..
core	[Build] Add COMMIT_SHA to caffe2::GetBuildOptions (#141313)	2024-11-26 00:09:36 +00:00
perfkernels	[caffe2] Add AVX512 support for box_cox operator (#143627)	2025-01-07 09:54:39 +00:00
serialize	Add option to serialization config to reduce random reads from get_record_offset when loading with mmap=True (#143880)	2025-01-31 17:09:20 +00:00
utils	Re-enable some C++ warnings (#142332)	2024-12-12 04:02:12 +00:00
.clang-format	[BE][clang-format] make macro PyObject_HEAD_INIT(type) and PyVarObject_HEAD_INIT(type, size) have its own line (#136949)	2024-10-02 18:39:22 +00:00
CMakeLists.txt	[Submodule] Turning flash-attention integration into 3rd party submod (#144120) (#146372)	2025-02-26 00:10:59 +00:00
unexported_symbols.lds	Hide all symbols in llvm namespace (#63272)	2021-08-15 11:29:43 -07:00
version_script.lds	Hide all symbols in llvm namespace (#63272)	2021-08-15 11:29:43 -07:00