sycl : add flash-attn support for head size 512 (#21654)
* sycl : add flash-attn support for head size 512 This patch extends the SYCL Flash Attention implementation to support head sizes (DKQ/DV) of 512. Changes: - Added DKQ/DV 512 cases to both tile and vector Flash Attention kernels. - Updated kernel selection logic to allow vector kernels for head sizes up to 512 (previously 256). - Removed unused/redundant AMD and RDNA-specific configuration functions in `fattn-tile.hpp`. - Refactored `ggml_backend_sycl_buffer_init_tensor` to use a switch statement for clearer tensor extra buffer initialization. - Added necessary template instances for the new 512 head size across various quantization types. * remove defunct mxfp4 reorder from setting buffer type
This commit is contained in:
@@ -67,6 +67,12 @@ static constexpr uint32_t ggml_sycl_fattn_tile_get_config_fp16(const int DKQ, co
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(256, 256, 16, 256, 2, 64, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(256, 256, 32, 256, 2, 64, 64)
|
||||
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(512, 512, 2, 64, 2, 64, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(512, 512, 4, 128, 2, 64, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(512, 512, 8, 256, 2, 64, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(512, 512, 16, 256, 2, 64, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(512, 512, 32, 256, 2, 64, 64)
|
||||
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(576, 512, 4, 128, 2, 64, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(576, 512, 8, 256, 2, 64, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(576, 512, 16, 256, 2, 64, 64)
|
||||
@@ -124,6 +130,12 @@ static constexpr uint32_t ggml_sycl_fattn_tile_get_config_fp32(const int DKQ, co
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(256, 256, 16, 256, 2, 32, 128)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(256, 256, 32, 256, 2, 32, 64)
|
||||
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(512, 512, 2, 128, 2, 64, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(512, 512, 4, 128, 2, 64, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(512, 512, 8, 256, 2, 64, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(512, 512, 16, 256, 2, 64, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(512, 512, 32, 256, 2, 64, 64)
|
||||
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(576, 512, 4, 128, 2, 32, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(576, 512, 8, 256, 2, 32, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(576, 512, 16, 256, 2, 32, 64)
|
||||
@@ -131,134 +143,6 @@ static constexpr uint32_t ggml_sycl_fattn_tile_get_config_fp32(const int DKQ, co
|
||||
return 0;
|
||||
}
|
||||
|
||||
static constexpr uint32_t ggml_sycl_fattn_tile_get_config_amd(const int DKQ, const int DV, const int ncols) {
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 40, 40, 2, 64, 2, 32, 40)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 40, 40, 4, 128, 2, 32, 40)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 40, 40, 8, 256, 2, 32, 40)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 40, 40, 16, 256, 2, 32, 40)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 40, 40, 32, 256, 2, 32, 40)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 40, 40, 64, 256, 2, 32, 40)
|
||||
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 64, 64, 2, 64, 3, 32, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 64, 64, 4, 128, 3, 64, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 64, 64, 8, 128, 2, 32, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 64, 64, 16, 256, 2, 128, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 64, 64, 32, 256, 2, 64, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 64, 64, 64, 256, 2, 64, 64)
|
||||
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 72, 72, 2, 64, 2, 32, 72)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 72, 72, 4, 128, 2, 32, 72)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 72, 72, 8, 256, 2, 32, 72)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 72, 72, 16, 256, 2, 32, 72)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 72, 72, 32, 256, 2, 32, 72)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 72, 72, 64, 256, 2, 32, 72)
|
||||
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 80, 80, 2, 64, 2, 32, 40)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 80, 80, 4, 128, 2, 32, 40)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 80, 80, 8, 256, 2, 32, 40)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 80, 80, 16, 256, 2, 32, 40)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 80, 80, 32, 256, 2, 32, 40)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 80, 80, 64, 256, 2, 32, 40)
|
||||
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 96, 96, 2, 64, 2, 32, 48)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 96, 96, 4, 128, 2, 32, 48)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 96, 96, 8, 256, 2, 32, 48)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 96, 96, 16, 256, 2, 32, 48)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 96, 96, 32, 256, 2, 32, 48)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 96, 96, 64, 256, 2, 32, 48)
|
||||
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(112, 112, 2, 64, 2, 32, 56)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(112, 112, 4, 128, 2, 32, 56)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(112, 112, 8, 256, 2, 32, 56)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(112, 112, 16, 256, 2, 32, 56)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(112, 112, 32, 256, 2, 32, 56)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(112, 112, 64, 256, 2, 32, 56)
|
||||
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(128, 128, 2, 256, 2, 128, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(128, 128, 4, 128, 2, 64, 128)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(128, 128, 8, 256, 2, 64, 128)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(128, 128, 16, 256, 2, 64, 128)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(128, 128, 32, 256, 2, 64, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(128, 128, 64, 256, 2, 64, 32)
|
||||
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(256, 256, 2, 256, 2, 128, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(256, 256, 4, 256, 2, 64, 128)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(256, 256, 8, 256, 2, 64, 128)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(256, 256, 16, 256, 2, 32, 128)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(256, 256, 32, 256, 2, 32, 128)
|
||||
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(576, 512, 4, 128, 2, 64, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(576, 512, 8, 256, 2, 64, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(576, 512, 16, 256, 2, 64, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(576, 512, 32, 512, 1, 128, 64)
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static constexpr uint32_t ggml_sycl_fattn_tile_get_config_amd_rdna(const int DKQ, const int DV, const int ncols) {
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 40, 40, 2, 64, 2, 32, 40)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 40, 40, 4, 128, 2, 32, 40)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 40, 40, 8, 256, 2, 32, 40)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 40, 40, 16, 256, 2, 32, 40)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 40, 40, 32, 256, 2, 32, 40)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 40, 40, 64, 256, 2, 32, 40)
|
||||
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 64, 64, 2, 64, 8, 32, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 64, 64, 4, 64, 8, 32, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 64, 64, 8, 128, 5, 128, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 64, 64, 16, 128, 5, 128, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 64, 64, 32, 128, 4, 64, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 64, 64, 64, 128, 5, 64, 64)
|
||||
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 72, 72, 2, 64, 2, 32, 72)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 72, 72, 4, 128, 2, 32, 72)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 72, 72, 8, 256, 2, 32, 72)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 72, 72, 16, 256, 2, 32, 72)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 72, 72, 32, 256, 2, 32, 72)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 72, 72, 64, 256, 2, 32, 72)
|
||||
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 80, 80, 2, 64, 2, 32, 40)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 80, 80, 4, 128, 2, 32, 40)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 80, 80, 8, 256, 2, 32, 40)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 80, 80, 16, 256, 2, 32, 40)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 80, 80, 32, 256, 2, 32, 40)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 80, 80, 64, 256, 2, 32, 40)
|
||||
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 96, 96, 2, 64, 2, 32, 48)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 96, 96, 4, 128, 2, 32, 48)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 96, 96, 8, 256, 2, 32, 48)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 96, 96, 16, 256, 2, 32, 48)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 96, 96, 32, 256, 2, 32, 48)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE( 96, 96, 64, 256, 2, 32, 48)
|
||||
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(112, 112, 2, 64, 2, 32, 56)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(112, 112, 4, 128, 2, 32, 56)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(112, 112, 8, 256, 2, 32, 56)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(112, 112, 16, 256, 2, 32, 56)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(112, 112, 32, 256, 2, 32, 56)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(112, 112, 64, 256, 2, 32, 56)
|
||||
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(128, 128, 2, 64, 8, 32, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(128, 128, 4, 128, 8, 64, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(128, 128, 8, 128, 8, 64, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(128, 128, 16, 256, 3, 128, 128)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(128, 128, 32, 256, 3, 128, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(128, 128, 64, 256, 3, 64, 64)
|
||||
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(256, 256, 2, 64, 8, 32, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(256, 256, 4, 128, 6, 32, 256)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(256, 256, 8, 128, 6, 32, 256)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(256, 256, 16, 256, 5, 32, 256)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(256, 256, 32, 256, 3, 64, 128)
|
||||
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(576, 512, 4, 128, 2, 64, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(576, 512, 8, 256, 2, 64, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(576, 512, 16, 256, 4, 64, 64)
|
||||
GGML_SYCL_FATTN_TILE_CONFIG_CASE(576, 512, 32, 256, 2, 128, 64)
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static constexpr uint32_t ggml_sycl_fattn_tile_get_config(const int DKQ, const int DV, const int ncols, const int cc) {
|
||||
if(fast_fp16_available(cc))
|
||||
return ggml_sycl_fattn_tile_get_config_fp16(DKQ, DV, ncols);
|
||||
@@ -1293,6 +1177,16 @@ static void launch_fattn_tile_switch_ncols2(ggml_backend_sycl_context & ctx, ggm
|
||||
launch_fattn_tile_switch_ncols1<DKQ, DV, 4, use_logit_softcap>(ctx, dst);
|
||||
return;
|
||||
}
|
||||
// ncols2=2 and ncols2=1 fallbacks only for cases where ncols=2 config exists (DKQ == DV).
|
||||
// For DKQ == 576, DV == 512 only GQA-optimized variants are implemented.
|
||||
if constexpr (DKQ == DV) {
|
||||
if (use_gqa_opt && gqa_ratio % 2 == 0) {
|
||||
launch_fattn_tile_switch_ncols1<DKQ, DV, 2, use_logit_softcap>(ctx, dst);
|
||||
return;
|
||||
}
|
||||
launch_fattn_tile_switch_ncols1<DKQ, DV, 1, use_logit_softcap>(ctx, dst);
|
||||
return;
|
||||
}
|
||||
}
|
||||
|
||||
if constexpr (DV <= 256) {
|
||||
@@ -1347,5 +1241,6 @@ extern DECL_FATTN_TILE_CASE( 96, 96);
|
||||
extern DECL_FATTN_TILE_CASE(112, 112);
|
||||
extern DECL_FATTN_TILE_CASE(128, 128);
|
||||
extern DECL_FATTN_TILE_CASE(256, 256);
|
||||
extern DECL_FATTN_TILE_CASE(512, 512);
|
||||
extern DECL_FATTN_TILE_CASE(576, 512);
|
||||
|
||||
|
||||
Reference in New Issue
Block a user