Skip to content

Enable HDIMDIFF64 #84

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Aug 26, 2025
Merged

Enable HDIMDIFF64 #84

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ce83b0f
Enable HDIMDIFF64
MatthewBonanni Aug 25, 2025
1420e6a
Add instantiations
MatthewBonanni Aug 25, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -185,8 +185,8 @@ if (FA3_ENABLED AND ${CMAKE_CUDA_COMPILER_VERSION} GREATER_EQUAL 12.0)
"hopper/instantiations/flash_fwd_hdim256_bf16*_sm90.cu")
# Add these for hdim diff cases
file(GLOB FA3_BF16_GEN_SRCS_
# "hopper/instantiations/flash_fwd_hdim64_256_bf16*_sm90.cu"
# "hopper/instantiations/flash_fwd_hdim64_512_bf16*_sm90.cu"
"hopper/instantiations/flash_fwd_hdim64_256_bf16*_sm90.cu"
"hopper/instantiations/flash_fwd_hdim64_512_bf16*_sm90.cu"
"hopper/instantiations/flash_fwd_hdim192_128_bf16*_sm90.cu")
list(APPEND FA3_BF16_GEN_SRCS ${FA3_BF16_GEN_SRCS_})
file(GLOB FA3_BF16_GEN_SRCS_
Expand All @@ -202,8 +202,8 @@ if (FA3_ENABLED AND ${CMAKE_CUDA_COMPILER_VERSION} GREATER_EQUAL 12.0)
"hopper/instantiations/flash_fwd_hdim256_fp16*_sm90.cu")
# Add these for hdim diff cases
file(GLOB FA3_FP16_GEN_SRCS_
# "hopper/instantiations/flash_fwd_hdim64_256_fp16*_sm90.cu"
# "hopper/instantiations/flash_fwd_hdim64_512_fp16*_sm90.cu"
"hopper/instantiations/flash_fwd_hdim64_256_fp16*_sm90.cu"
"hopper/instantiations/flash_fwd_hdim64_512_fp16*_sm90.cu"
"hopper/instantiations/flash_fwd_hdim192_128_fp16*_sm90.cu")
list(APPEND FA3_FP16_GEN_SRCS ${FA3_FP16_GEN_SRCS_})
file(GLOB FA3_FP16_GEN_SRCS_
Expand Down Expand Up @@ -272,7 +272,7 @@ if (FA3_ENABLED AND ${CMAKE_CUDA_COMPILER_VERSION} GREATER_EQUAL 12.0)
FLASHATTENTION_VARLEN_ONLY # Custom flag to save on binary size
FLASHATTENTION_DISABLE_CLUSTER # disabled for varlen in any case
# FLASHATTENTION_DISABLE_SM8x
FLASHATTENTION_DISABLE_HDIMDIFF64
# FLASHATTENTION_DISABLE_HDIMDIFF64
# FLASHATTENTION_DISABLE_HDIMDIFF192
CUTE_SM90_EXTENDED_MMA_SHAPES_ENABLED
CUTLASS_ENABLE_GDC_FOR_SM90
Expand Down