EngineX-Ascend/enginex-ascend-910-llama.cpp
10
0
Fork 0
Code Issues Pull Requests Actions 4 Projects Releases Wiki Activity

metal : mark FA blocks (#16372)

Browse Source 
* metal : better unroll in the FA kernels

* metal : index FA blocks

* tests : restore [no ci]

* metal : prevent division by zero in FA kernels

* metal : fix -INF detection logic
This commit is contained in:
Georgi Gerganov
2025-10-08 10:57:53 +03:00
committed by GitHub
parent 7fdd16b432
commit b2c08c9ec4
7 changed files with 324 additions and 65 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
ggml/src/ggml-metal/ggml-metal-impl.h
View File

@@ -70,11 +70,19 @@
// function constants offsets
#define FC_FLASH_ATTN_EXT_PAD 100
#define FC_FLASH_ATTN_EXT 200
#define FC_FLASH_ATTN_EXT_VEC 300
#define FC_FLASH_ATTN_EXT_VEC_REDUCE 400
#define FC_MUL_MV 500
#define FC_MUL_MM 600
#define FC_FLASH_ATTN_EXT_BLK 200
#define FC_FLASH_ATTN_EXT 300
#define FC_FLASH_ATTN_EXT_VEC 400
#define FC_FLASH_ATTN_EXT_VEC_REDUCE 500
#define FC_MUL_MV 600
#define FC_MUL_MM 700
// op-specific constants
#define OP_FLASH_ATTN_EXT_NQPTG 8
#define OP_FLASH_ATTN_EXT_NCPSG 64
#define OP_FLASH_ATTN_EXT_VEC_NQPTG 1
#define OP_FLASH_ATTN_EXT_VEC_NCPSG 32
// kernel argument structs
//
@@ -263,6 +271,17 @@ typedef struct {
uint64_t nb33;
} ggml_metal_kargs_flash_attn_ext_pad;
typedef struct {
int32_t ne01;
int32_t ne30;
int32_t ne31;
int32_t ne32;
int32_t ne33;
uint64_t nb31;
uint64_t nb32;
uint64_t nb33;
} ggml_metal_kargs_flash_attn_ext_blk;
typedef struct {
int32_t ne01;
int32_t ne02;