diff options
| author | Johannes Gäßler <johannesg@5d6.de> | 2024-05-12 19:40:45 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-05-12 19:40:45 +0200 |
| commit | dc685be46622a8fabfd57cfa804237c8f15679b8 (patch) | |
| tree | 43b1baf9bb0ab8d39e68f0e865a34fad37a59370 /tests/test-backend-ops.cpp | |
| parent | 6f1b63606fc68a09d62d1d74dbd156c35219026d (diff) | |
CUDA: add FP32 FlashAttention vector kernel (#7188)
* CUDA: add FP32 FlashAttention vector kernel
* fixup! CUDA: add FP32 FlashAttention vector kernel
* fixup! fixup! CUDA: add FP32 FlashAttention vector kernel
* fixup! fixup! fixup! CUDA: add FP32 FlashAttention vector kernel
Diffstat (limited to 'tests/test-backend-ops.cpp')
| -rw-r--r-- | tests/test-backend-ops.cpp | 5 |
1 files changed, 1 insertions, 4 deletions
diff --git a/tests/test-backend-ops.cpp b/tests/test-backend-ops.cpp index 731788b9..45a2cb85 100644 --- a/tests/test-backend-ops.cpp +++ b/tests/test-backend-ops.cpp @@ -2,6 +2,7 @@ #include <ggml-alloc.h> #include <ggml-backend.h> #include <ggml-backend-impl.h> + #include <algorithm> #include <array> #include <cfloat> @@ -2173,11 +2174,7 @@ static bool test_backend(ggml_backend_t backend, test_mode mode, const char * op test_cases.emplace_back(new test_timestep_embedding()); test_cases.emplace_back(new test_leaky_relu()); -#if defined(GGML_USE_HIPBLAS) && defined(__HIP_PLATFORM_AMD__) - for (int hs : { 64, 128, }) { // other head sizes not implemented -#else for (int hs : { 64, 80, 128, 256, }) { -#endif // defined(GGML_USE_HIPBLAS) && defined(__HIP_PLATFORM_AMD__) for (float max_bias : {0.0f, 8.0f}) { for (int nh : { 32, }) { for (int kv : { 512, 1024, }) { |