Skip to content

Faster DeepSeek FA on CUDA #408

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 3 commits into from
May 12, 2025
Merged

Faster DeepSeek FA on CUDA #408

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
130cdf2
New DeepSeek FlashMLA
May 11, 2025
d1601d4
Rearrange MLA K cache so it first new CUDA FA implementation
May 11, 2025
d7008ad
constexpr and minor changes
May 11, 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
2 changes: 1 addition & 1 deletion ggml/src/CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -986,7 +986,7 @@ endif()
set(CUDA_CXX_FLAGS "")

if (GGML_CUDA)
set(CUDA_FLAGS -use_fast_math)
set(CUDA_FLAGS -use_fast_math -extended-lambda)

if (GGML_FATAL_WARNINGS)
list(APPEND CUDA_FLAGS -Werror all-warnings)
Expand Down
10 changes: 10 additions & 0 deletions ggml/src/ggml-cuda/cp-async.cuh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,16 @@

#include "common.cuh"

static __device__ __forceinline__ unsigned int ggml_cuda_cvta_generic_to_shared(void * generic_ptr) {
#ifdef CP_ASYNC_AVAILABLE
return __cvta_generic_to_shared(generic_ptr);
#else
GGML_UNUSED(generic_ptr);
NO_DEVICE_CODE;
return 0;
#endif // CP_ASYNC_AVAILABLE
}

// Copies data from global to shared memory, cg == cache global.
// Both the src and dst pointers must be aligned to 16 bit.
// Shared memory uses 32 bit addressing, the pointer is passed as unsigned int.
Expand Down
Loading