tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-20 06:36:48 -04:00
Code Issues Packages Projects Releases Wiki Activity

metal : support FA without mask + add asserts (#7278)

Browse Source 
* ggml : fa without mask + add asserts

ggml-ci

* metal : support non-contiguous KV

ggml-ci
This commit is contained in:
Georgi Gerganov
2024-05-14 19:09:30 +03:00
committed by GitHub
parent a5e3fde857
commit e8a7fd4fb0
5 changed files with 85 additions and 75 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
ggml.h
View File

@@ -766,7 +766,8 @@ extern "C" {
GGML_API bool ggml_is_3d (const struct ggml_tensor * tensor);
GGML_API int ggml_n_dims (const struct ggml_tensor * tensor); // returns 1 for scalars
GGML_API bool ggml_are_same_shape(const struct ggml_tensor * t0, const struct ggml_tensor * t1);
GGML_API bool ggml_are_same_shape (const struct ggml_tensor * t0, const struct ggml_tensor * t1);
GGML_API bool ggml_are_same_stride(const struct ggml_tensor * t0, const struct ggml_tensor * t1);
// use this to compute the memory overhead of a tensor
GGML_API size_t ggml_tensor_overhead(void);