sleepy/llama.cpp
1
0
Fork 0
Code Issues 11 Pull Requests Actions 109 Packages Projects Releases Wiki Activity

ggml-cuda: add flash-attn support for DKQ=320/DV=256 with ncols2=32 (… (#22286)

Browse Source 
* ggml-cuda: add flash-attn support for DKQ=320/DV=256 with ncols2=32 (GQA=32)

Adds MMA-f16 and tile kernel configs, dispatch logic, template instances,
and tile .cu file for Mistral Small 4 (head sizes 320/256), restricting to
ncols2=32 to support GQA ratio 32 only.

* Adding check to return BEST_FATTN_KERNEL_NONE in case GQA!=32

* Apply suggestions from code review

Address review comments

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

* Address review comments and making kernel config default to DQK=512, DV=512 instead of DQK=256,DV=256

* Fixed bug with sinks=1, with ncols=32, there are two warp-groups created but sinks index is same(0,...,15) for both the groups hence with sinks=1, output is not matching with CPU output. Added sink_base which will be base index for each warp_group (threadIdx.y / np)

* Apply suggestions from code review

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

* Update ggml/src/ggml-cuda/template-instances/generate_cu_files.py

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
This commit is contained in:
lnigam
2026-04-29 01:07:35 +05:30
committed by GitHub
parent 5d56effdee
commit 7b8443ac78
8 changed files with 86 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/fattn-mma-f16.cuh
+14 -1
View File
@@ -66,6 +66,9 @@ static constexpr __host__ __device__ fattn_mma_config ggml_cuda_fattn_mma_get_co
GGML_CUDA_FATTN_MMA_CONFIG_CASE(256, 256, 32, 128, 2, 32, 128, 128, 128, 2, true);
GGML_CUDA_FATTN_MMA_CONFIG_CASE(256, 256, 64, 128, 2, 32, 128, 128, 128, 2, true);
GGML_CUDA_FATTN_MMA_CONFIG_CASE(320, 256, 32, 128, 2, 32, 128, 128, 128, 1, false);
GGML_CUDA_FATTN_MMA_CONFIG_CASE(320, 256, 64, 256, 1, 32, 128, 128, 128, 1, false);
GGML_CUDA_FATTN_MMA_CONFIG_CASE(512, 512, 8, 64, 4, 32, 256, 256, 128, 1, false);
GGML_CUDA_FATTN_MMA_CONFIG_CASE(512, 512, 16, 64, 4, 32, 256, 256, 128, 1, false);
GGML_CUDA_FATTN_MMA_CONFIG_CASE(512, 512, 32, 128, 2, 32, 128, 128, 128, 1, false);
@@ -85,6 +88,9 @@ static constexpr __host__ __device__ fattn_mma_config ggml_cuda_fattn_mma_get_co
GGML_CUDA_FATTN_MMA_CONFIG_CASE(256, 256, 32, 128, 2, 64, 128, 128, 64, 2, true);
GGML_CUDA_FATTN_MMA_CONFIG_CASE(256, 256, 64, 128, 2, 64, 128, 128, 64, 2, true);
GGML_CUDA_FATTN_MMA_CONFIG_CASE(320, 256, 32, 128, 2, 32, 128, 128, 128, 1, false);
GGML_CUDA_FATTN_MMA_CONFIG_CASE(320, 256, 64, 256, 1, 32, 128, 128, 128, 1, false);
GGML_CUDA_FATTN_MMA_CONFIG_CASE(512, 512, 8, 64, 4, 32, 96, 64, 128, 1, false);
GGML_CUDA_FATTN_MMA_CONFIG_CASE(512, 512, 16, 64, 4, 32, 96, 64, 128, 1, false);
GGML_CUDA_FATTN_MMA_CONFIG_CASE(512, 512, 32, 128, 2, 32, 128, 128, 128, 1, false);
@@ -118,6 +124,9 @@ static constexpr __host__ __device__ fattn_mma_config ggml_cuda_fattn_mma_get_co
GGML_CUDA_FATTN_MMA_CONFIG_CASE(256, 256, 32, 128, 2, 64, 128, 128, 64, 2, true);
GGML_CUDA_FATTN_MMA_CONFIG_CASE(256, 256, 64, 128, 2, 64, 128, 128, 64, 2, true);
GGML_CUDA_FATTN_MMA_CONFIG_CASE(320, 256, 32, 128, 2, 64, 160, 128, 64, 2, true);
GGML_CUDA_FATTN_MMA_CONFIG_CASE(320, 256, 64, 128, 2, 64, 160, 128, 64, 2, false);
GGML_CUDA_FATTN_MMA_CONFIG_CASE(512, 512, 16, 64, 4, 32, 128, 128, 128, 1, false);
GGML_CUDA_FATTN_MMA_CONFIG_CASE(512, 512, 32, 128, 2, 32, 128, 128, 128, 1, false);
GGML_CUDA_FATTN_MMA_CONFIG_CASE(512, 512, 64, 256, 1, 32, 128, 128, 128, 1, false);
@@ -1217,7 +1226,7 @@ static __device__ __forceinline__ void flash_attn_ext_f16_process_tile(
float KQ_max_scale[cols_per_thread];
#pragma unroll
for (int col = 0; col < cols_per_thread; ++col) {
const int jc = cols_per_warp == 8 ? T_C_KQ::get_j(col) : T_C_KQ::get_i(2*col);
const int jc = (threadIdx.y/np)*cols_per_warp + (cols_per_warp == 8 ? T_C_KQ::get_j(col) : T_C_KQ::get_i(2*col));
const float sink = sinks_f[jc % ncols2];
const float KQ_max_new = fmaxf(KQ_max[col], sink);
@@ -1825,6 +1834,10 @@ extern DECL_FATTN_MMA_F16_CASE(576, 512, 1, 16);
extern DECL_FATTN_MMA_F16_CASE(576, 512, 2, 16);
extern DECL_FATTN_MMA_F16_CASE(576, 512, 4, 16);
// Mistral Small 4 (DKQ=320, DV=256), GQA=32-only build:
extern DECL_FATTN_MMA_F16_CASE(320, 256, 1, 32);
extern DECL_FATTN_MMA_F16_CASE(320, 256, 2, 32);
// For GLM 4.7 Flash
extern DECL_FATTN_MMA_F16_CASE(576, 512, 4, 4);
extern DECL_FATTN_MMA_F16_CASE(576, 512, 8, 4);
ggml/src/ggml-cuda/fattn-tile.cu
+4
View File
@@ -38,6 +38,10 @@ void ggml_cuda_flash_attn_ext_tile(ggml_backend_cuda_context & ctx, ggml_tensor
GGML_ASSERT(V->ne[0] == K->ne[0]);
ggml_cuda_flash_attn_ext_tile_case<256, 256>(ctx, dst);
} break;
case 320: {
GGML_ASSERT(V->ne[0] == 256);
ggml_cuda_flash_attn_ext_tile_case<320, 256>(ctx, dst);
} break;
case 512: {
GGML_ASSERT(V->ne[0] == K->ne[0]);
ggml_cuda_flash_attn_ext_tile_case<512, 512>(ctx, dst);
ggml/src/ggml-cuda/fattn-tile.cuh
+28 -9
View File
@@ -68,6 +68,8 @@ static constexpr __host__ __device__ uint32_t ggml_cuda_fattn_tile_get_config_nv
GGML_CUDA_FATTN_TILE_CONFIG_CASE(256, 256, 16, 256, 2, 64, 64)
GGML_CUDA_FATTN_TILE_CONFIG_CASE(256, 256, 32, 256, 2, 64, 64)
GGML_CUDA_FATTN_TILE_CONFIG_CASE(320, 256, 32, 256, 2, 64, 64)
GGML_CUDA_FATTN_TILE_CONFIG_CASE(512, 512, 4, 128, 2, 64, 64)
GGML_CUDA_FATTN_TILE_CONFIG_CASE(512, 512, 8, 256, 2, 64, 64)
GGML_CUDA_FATTN_TILE_CONFIG_CASE(512, 512, 16, 256, 2, 64, 64)
@@ -128,6 +130,8 @@ static constexpr __host__ __device__ uint32_t ggml_cuda_fattn_tile_get_config_nv
GGML_CUDA_FATTN_TILE_CONFIG_CASE(256, 256, 16, 256, 2, 32, 128)
GGML_CUDA_FATTN_TILE_CONFIG_CASE(256, 256, 32, 256, 2, 32, 64)
GGML_CUDA_FATTN_TILE_CONFIG_CASE(320, 256, 32, 256, 2, 32, 64)
GGML_CUDA_FATTN_TILE_CONFIG_CASE(512, 512, 4, 128, 2, 32, 64)
GGML_CUDA_FATTN_TILE_CONFIG_CASE(512, 512, 8, 256, 2, 32, 64)
GGML_CUDA_FATTN_TILE_CONFIG_CASE(512, 512, 16, 256, 2, 32, 64)
@@ -195,6 +199,8 @@ static constexpr __host__ __device__ uint32_t ggml_cuda_fattn_tile_get_config_am
GGML_CUDA_FATTN_TILE_CONFIG_CASE(256, 256, 16, 256, 2, 32, 128)
GGML_CUDA_FATTN_TILE_CONFIG_CASE(256, 256, 32, 256, 2, 32, 128)
GGML_CUDA_FATTN_TILE_CONFIG_CASE(320, 256, 32, 512, 1, 128, 64)
GGML_CUDA_FATTN_TILE_CONFIG_CASE(512, 512, 4, 128, 2, 64, 64)
GGML_CUDA_FATTN_TILE_CONFIG_CASE(512, 512, 8, 256, 2, 64, 64)
GGML_CUDA_FATTN_TILE_CONFIG_CASE(512, 512, 16, 256, 2, 64, 64)
@@ -264,6 +270,8 @@ static constexpr __host__ __device__ uint32_t ggml_cuda_fattn_tile_get_config_am
GGML_CUDA_FATTN_TILE_CONFIG_CASE(256, 256, 16, 256, 5, 32, 256)
GGML_CUDA_FATTN_TILE_CONFIG_CASE(256, 256, 32, 256, 3, 64, 128)
GGML_CUDA_FATTN_TILE_CONFIG_CASE(320, 256, 32, 256, 2, 128, 64)
GGML_CUDA_FATTN_TILE_CONFIG_CASE(512, 512, 4, 128, 2, 64, 64)
GGML_CUDA_FATTN_TILE_CONFIG_CASE(512, 512, 8, 256, 2, 64, 64)
GGML_CUDA_FATTN_TILE_CONFIG_CASE(512, 512, 16, 256, 4, 64, 64)
@@ -1144,14 +1152,16 @@ static void launch_fattn_tile_switch_ncols1(ggml_backend_cuda_context & ctx, ggm
}
}
if (Q->ne[1] > 8/ncols2) {
constexpr int cols_per_block = 16;
const int nwarps = ggml_cuda_fattn_tile_get_nthreads (DKQ, DV, cols_per_block, cc) / warp_size;
const int nbatch_fa = ggml_cuda_fattn_tile_get_nbatch_fa(DKQ, DV, cols_per_block, cc);
fattn_kernel_t fattn_kernel = flash_attn_tile<DKQ, DV, cols_per_block/ncols2, ncols2, use_logit_softcap>;
launch_fattn<DV, cols_per_block/ncols2, ncols2>
(ctx, dst, fattn_kernel, nwarps, nbytes_shared, nbatch_fa, true, true, false, warp_size);
return;
if constexpr (ncols2 <= 16) {
if (Q->ne[1] > 8/ncols2) {
constexpr int cols_per_block = 16;
const int nwarps = ggml_cuda_fattn_tile_get_nthreads (DKQ, DV, cols_per_block, cc) / warp_size;
const int nbatch_fa = ggml_cuda_fattn_tile_get_nbatch_fa(DKQ, DV, cols_per_block, cc);
fattn_kernel_t fattn_kernel = flash_attn_tile<DKQ, DV, cols_per_block/ncols2, ncols2, use_logit_softcap>;
launch_fattn<DV, cols_per_block/ncols2, ncols2>
(ctx, dst, fattn_kernel, nwarps, nbytes_shared, nbatch_fa, true, true, false, warp_size);
return;
}
}
if constexpr (ncols2 <= 8) {
@@ -1210,6 +1220,14 @@ static void launch_fattn_tile_switch_ncols2(ggml_backend_cuda_context & ctx, ggm
const int gqa_limit = nvidia && gqa_ratio <= 4 && DV <= 256 ? 16 : INT_MAX;
const bool use_gqa_opt = mask && max_bias == 0.0f && Q->ne[1] <= gqa_limit && K->ne[1] % FATTN_KQ_STRIDE == 0;
if constexpr (DKQ == 320) { // Mistral Small 4
if (use_gqa_opt && gqa_ratio % 32 == 0) {
launch_fattn_tile_switch_ncols1<DKQ, DV, 32, use_logit_softcap>(ctx, dst);
return;
}
GGML_ABORT("flash-attn tile (320/256): expected GQA ratio multiple of 32");
}
if constexpr (DKQ == 576) {
if (use_gqa_opt && gqa_ratio % 16 == 0) {
launch_fattn_tile_switch_ncols1<DKQ, DV, 16, use_logit_softcap>(ctx, dst);
@@ -1221,7 +1239,7 @@ static void launch_fattn_tile_switch_ncols2(ggml_backend_cuda_context & ctx, ggm
}
}
if constexpr (DKQ <= 512) {
if constexpr (DKQ <= 512 && DKQ != 320) {
if (use_gqa_opt && gqa_ratio % 8 == 0) {
launch_fattn_tile_switch_ncols1<DKQ, DV, 8, use_logit_softcap>(ctx, dst);
return;
@@ -1275,5 +1293,6 @@ 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(320, 256);
extern DECL_FATTN_TILE_CASE(512, 512);
extern DECL_FATTN_TILE_CASE(576, 512);
ggml/src/ggml-cuda/fattn.cu
+24
View File
@@ -143,6 +143,22 @@ static void ggml_cuda_flash_attn_ext_mma_f16(ggml_backend_cuda_context & ctx, gg
GGML_ASSERT(V->ne[0] == 256);
ggml_cuda_flash_attn_ext_mma_f16_switch_ncols2<256, 256>(ctx, dst);
break;
case 320:
// For Mistral Small 4, go straight to the ncols1 switch (ncols2=32-only build).
GGML_ASSERT(V->ne[0] == 256);
{
float max_bias = 0.0f;
memcpy(&max_bias, (const float *) KQV->op_params + 1, sizeof(float));
const bool use_gqa_opt = mask && max_bias == 0.0f;
GGML_ASSERT(use_gqa_opt);
GGML_ASSERT(Q->ne[2] % K->ne[2] == 0);
const int gqa_ratio = Q->ne[2] / K->ne[2];
GGML_ASSERT(gqa_ratio % 32 == 0);
ggml_cuda_flash_attn_ext_mma_f16_switch_ncols1<320, 256, 32>(ctx, dst);
}
break;
case 512:
GGML_ASSERT(V->ne[0] == 512);
ggml_cuda_flash_attn_ext_mma_f16_switch_ncols2<512, 512>(ctx, dst);
@@ -352,6 +368,14 @@ static best_fattn_kernel ggml_cuda_get_best_fattn_kernel(const int device, const
return BEST_FATTN_KERNEL_NONE;
}
break;
case 320:
if (V->ne[0] != 256 || !gqa_opt_applies) {
return BEST_FATTN_KERNEL_NONE;
}
if (gqa_ratio % 32 != 0) {
return BEST_FATTN_KERNEL_NONE;
}
break;
case 512:
if (V->ne[0] != K->ne[0]) {
return BEST_FATTN_KERNEL_NONE;
ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_32.cu
+1
View File
@@ -2,4 +2,5 @@
#include "../fattn-mma-f16.cuh"
DECL_FATTN_MMA_F16_CASE(320, 256, 1, 32);
DECL_FATTN_MMA_F16_CASE(576, 512, 1, 32);
ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_32.cu
+1
View File
@@ -2,4 +2,5 @@
#include "../fattn-mma-f16.cuh"
DECL_FATTN_MMA_F16_CASE(320, 256, 2, 32);
DECL_FATTN_MMA_F16_CASE(576, 512, 2, 32);
ggml/src/ggml-cuda/template-instances/fattn-tile-instance-dkq320-dv256.cu
+5
View File
@@ -0,0 +1,5 @@
// This file has been autogenerated by generate_cu_files.py, do not edit manually.
#include "../fattn-tile.cuh"
DECL_FATTN_TILE_CASE(320, 256);
ggml/src/ggml-cuda/template-instances/generate_cu_files.py
+9 -6
View File
@@ -3,7 +3,7 @@
from glob import glob
import os
HEAD_SIZES_KQ = [40, 64, 72, 80, 96, 112, 128, 256, 512, 576]
HEAD_SIZES_KQ = [40, 64, 72, 80, 96, 112, 128, 256, 320, 512, 576]
TYPES_KV = ["GGML_TYPE_F16", "GGML_TYPE_Q4_0", "GGML_TYPE_Q4_1", "GGML_TYPE_Q5_0", "GGML_TYPE_Q5_1", "GGML_TYPE_Q8_0", "GGML_TYPE_BF16"]
@@ -62,7 +62,7 @@ for filename in glob("*.cu"):
os.remove(filename)
for head_size_kq in HEAD_SIZES_KQ:
head_size_v = head_size_kq if head_size_kq != 576 else 512
head_size_v = 256 if head_size_kq == 320 else (head_size_kq if head_size_kq != 576 else 512)
with open(f"fattn-tile-instance-dkq{head_size_kq}-dv{head_size_v}.cu", "w") as f:
f.write(SOURCE_FATTN_TILE.format(head_size_kq=head_size_kq, head_size_v=head_size_v))
@@ -84,13 +84,16 @@ for ncols in [8, 16, 32, 64]:
continue
if head_size_kq == 72:
continue
if head_size_kq == 512 and ncols2 not in (4, 8):
# Skip compilation of unused ncols2 values for niche head sizes:
if head_size_kq == 320 and ncols2 != 32: # Mistral Small 4
continue
if head_size_kq != 576 and ncols2 in (16, 32):
if head_size_kq == 512 and ncols2 not in (4, 8): # Gemma 4
continue
if head_size_kq == 576 and ncols2 not in (4, 16, 32):
if head_size_kq == 576 and ncols2 not in (4, 16, 32): # Deepseek, GLM 4.7 Flash
continue
head_size_v = head_size_kq if head_size_kq != 576 else 512
if head_size_kq not in (320, 576) and ncols2 in (16, 32):
continue
head_size_v = 256 if head_size_kq == 320 else (head_size_kq if head_size_kq != 576 else 512)
f.write(SOURCE_FATTN_MMA_CASE.format(ncols1=ncols1, ncols2=ncols2, head_size_kq=head_size_kq, head_size_v=head_size_v))
for type in TYPES_MMQ: