upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-02 08:00:48 -05:00
Code Issues Packages Projects Releases Wiki Activity

HIP: remove rocWMMA FlashAttention (#26046)

Browse Source
This commit is contained in:
Johannes Gäßler
2026-07-24 17:53:54 +02:00
committed by GitHub
parent ed7adbfefd
commit fa72aeccb2
10 changed files with 5 additions and 798 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
CODEOWNERS
View File

@@ -60,7 +60,6 @@
/ggml/src/ggml-cpu/spacemit/ @alex-spacemit
/ggml/src/ggml-cuda/ @ggml-org/ggml-cuda
/ggml/src/ggml-cuda/vendors/hip.h @IMbackK
/ggml/src/ggml-cuda/fattn-wmma* @IMbackK
/ggml/src/ggml-hexagon/ @ggml-org/ggml-hexagon
/ggml/src/ggml-hip/ @IMbackK
/ggml/src/ggml-et/ @marty1885

6
docs/build.md
View File

@@ -361,12 +361,6 @@ You can download it from your Linux distro's package manager or from here: [ROCm
Note: `GPU_TARGETS` is optional, omitting it will build the code for all GPUs in the current system.
To enhance flash attention performance on RDNA3+ or CDNA architectures, you can utilize the rocWMMA library by enabling the `-DGGML_HIP_ROCWMMA_FATTN=ON` option. This requires rocWMMA headers to be installed on the build system.
The rocWMMA library is included by default when installing the ROCm SDK using the `rocm` meta package provided by AMD. Alternatively, if you are not using the meta package, you can install the library using the `rocwmma-dev` or `rocwmma-devel` package, depending on your system's package manager.
As an alternative, you can manually install the library by cloning it from the official [GitHub repository](https://github.com/ROCm/rocWMMA), checkout the corresponding version tag (e.g. `rocm-6.2.4`) and set `-DCMAKE_CXX_FLAGS="-I<path/to/rocwmma>/library/include/"` in CMake. This also works under Windows despite not officially supported by AMD.
Note that if you get the following error:
```
clang: error: cannot find ROCm device library; provide its path via '--rocm-path' or '--rocm-device-lib-path', or pass '-nogpulib' to build without ROCm device library

1
ggml/CMakeLists.txt
View File

@@ -216,7 +216,6 @@ option(GGML_HIP "ggml: use HIP"
option(GGML_HIP_GRAPHS "ggml: use HIP graph" ON)
option(GGML_HIP_RCCL "ggml: use ROCm Collective Comm. Library" OFF)
option(GGML_HIP_NO_VMM "ggml: do not try to use HIP VMM" ON)
option(GGML_HIP_ROCWMMA_FATTN "ggml: enable rocWMMA for FlashAttention" OFF)
option(GGML_HIP_MMQ_MFMA "ggml: enable MFMA MMA for CDNA in MMQ" ON)
option(GGML_HIP_EXPORT_METRICS "ggml: enable kernel perf metrics output" OFF)
option(GGML_MUSA_GRAPHS "ggml: use MUSA graph, experimental, unstable" OFF)

1
ggml/src/ggml-cuda/fattn-tile.cu
View File

@@ -1,6 +1,5 @@
#include "common.cuh"
#include "fattn-tile.cuh"
#include "fattn-wmma-f16.cuh"
void ggml_cuda_flash_attn_ext_tile(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
const ggml_tensor * K = dst->src[1];

8
ggml/src/ggml-cuda/fattn-tile.cuh
View File

@@ -1,6 +1,5 @@
#include "common.cuh"
#include "fattn-common.cuh"
#include "fattn-wmma-f16.cuh"
// nbatch_fa == number of KQ rows to process per iteration
// nbatch_K == number of K columns to load in parallel for KQ calculation
@@ -825,12 +824,7 @@ static __global__ void flash_attn_tile(
// Skip unused kernel variants for faster compilation:
if (
#ifdef GGML_USE_WMMA_FATTN
(ncols2 != 1 && DV != 40 && DV != 72 && DV != 512) ||
#endif // GGML_USE_WMMA_FATTN
(use_logit_softcap && !(DV == 128 || DV == 256 || DV == 512))
) {
if ((use_logit_softcap && !(DV == 128 || DV == 256 || DV == 512))) {
GGML_UNUSED_VARS(Q, K, V, mask, sinks, KV_max, dst, dst_meta, scale,
max_bias, m0, m1, n_head_log2, logit_softcap,
ne00, ne01, ne02, ne03,

705
ggml/src/ggml-cuda/fattn-wmma-f16.cu
View File

@@ -1,705 +0,0 @@
// Old and deprecated WMMA FlashAttention implementation.
// It is still needed for Volta since the memory layout of NVIDIA tensor cores changed with Turing.
// Long-term the WMMA code should be replaced with a dedicated Volta implementation.
#include "common.cuh"
#include "fattn-common.cuh"
#include "fattn-wmma-f16.cuh"
#ifdef GGML_USE_WMMA_FATTN
#if !defined(GGML_USE_HIP)
#include <mma.h>
#if defined(GGML_USE_MUSA)
namespace wmma = mtmusa::wmma;
#else // GGML_USE_MUSA
namespace wmma = nvcuda::wmma;
#endif // GGML_USE_MUSA
#elif defined(GGML_USE_HIP)
#include <rocwmma/rocwmma.hpp>
namespace wmma = rocwmma;
#endif // !defined(GGML_USE_HIP)
#endif // GGML_USE_WMMA_FATTN
// D == head size, VKQ_stride == num VKQ rows calculated in parallel:
template<int D, int ncols, int nwarps, int VKQ_stride, typename KQ_acc_t, bool use_logit_softcap>
__launch_bounds__(nwarps*ggml_cuda_get_physical_warp_size(), 1)
static __global__ void flash_attn_ext_f16(
const char * Q_ptr,
const char * K_ptr,
const char * V_ptr,
const char * mask_ptr,
const char * sinks_ptr,
const int * KV_max_ptr,
float * dst_ptr,
float2 * dst_meta_ptr,
const float scale,
const float max_bias,
const float m0,
const float m1,
const uint32_t n_head_log2,
const float logit_softcap,
const int32_t ne00, const uint3 ne01, const int32_t ne02, const int32_t ne03,
const int32_t nb01, const int32_t nb02, const int32_t nb03,
const int32_t ne10, const int32_t ne11, const int32_t ne12, const int32_t ne13,
const int32_t nb11, const int32_t nb12, const int64_t nb13,
const int32_t nb21, const int32_t nb22, const int64_t nb23,
const int32_t ne31, const int32_t ne32, const int32_t ne33,
const int32_t nb31, const int32_t nb32, const int64_t nb33) {
#if defined(FLASH_ATTN_AVAILABLE) && (defined(GGML_HIP_ROCWMMA_FATTN) && defined(GGML_USE_WMMA_FATTN))
const char * GGML_CUDA_RESTRICT Q = Q_ptr;
const char * GGML_CUDA_RESTRICT K = K_ptr;
const char * GGML_CUDA_RESTRICT V = V_ptr;
const char * GGML_CUDA_RESTRICT mask = mask_ptr;
const char * GGML_CUDA_RESTRICT sinks = sinks_ptr;
const int * GGML_CUDA_RESTRICT KV_max = KV_max_ptr;
float * GGML_CUDA_RESTRICT dst = dst_ptr;
float2 * GGML_CUDA_RESTRICT dst_meta = dst_meta_ptr;
// Skip unused kernel variants for faster compilation:
if (use_logit_softcap && !(D == 128 || D == 256)) {
NO_DEVICE_CODE;
return;
}
//In this kernel Q, K, V are matrices while i, j, k are matrix indices.
constexpr int warp_size = ggml_cuda_get_physical_warp_size();
const int ic0 = ncols*blockIdx.x; // Index of the first Q/QKV column to work on.
static_assert(D <= FATTN_KQ_STRIDE, "D must be <= FATTN_KQ_STRIDE.");
static_assert(ncols == 8 || ncols % 16 == 0, "ncols must be 8 or a multiple of 16.");
constexpr int frag_m = ncols == 8 ? 32 : 16;
constexpr int frag_n = ncols == 8 ? 8 : 16;
static_assert(D % frag_m == 0, "If ncols == 8 then D % frag_m must be 0.");
#if defined(GGML_USE_HIP) && HIP_VERSION >= 60500000
typedef wmma::fragment<wmma::matrix_a, frag_m, frag_n, 16, _Float16, wmma::row_major> frag_a_K;
typedef wmma::fragment<wmma::matrix_a, frag_m, frag_n, 16, _Float16, wmma::col_major> frag_a_V;
typedef wmma::fragment<wmma::matrix_b, frag_m, frag_n, 16, _Float16, wmma::col_major> frag_b;
typedef wmma::fragment<wmma::accumulator, frag_m, frag_n, 16, KQ_acc_t> frag_c_KQ;
typedef wmma::fragment<wmma::accumulator, frag_m, frag_n, 16, _Float16> frag_c_VKQ;
#else
typedef wmma::fragment<wmma::matrix_a, frag_m, frag_n, 16, half, wmma::row_major> frag_a_K;
typedef wmma::fragment<wmma::matrix_a, frag_m, frag_n, 16, half, wmma::col_major> frag_a_V;
typedef wmma::fragment<wmma::matrix_b, frag_m, frag_n, 16, half, wmma::col_major> frag_b;
typedef wmma::fragment<wmma::accumulator, frag_m, frag_n, 16, KQ_acc_t> frag_c_KQ;
typedef wmma::fragment<wmma::accumulator, frag_m, frag_n, 16, half> frag_c_VKQ;
#endif
constexpr int KQ_stride_tc = nwarps*frag_m; // Number of KQ rows calculated in parallel.
constexpr int VKQ_ratio = KQ_stride_tc/VKQ_stride; // Number of parallel VKQ accumulators needed to keep all warps busy.
static_assert(VKQ_ratio <= nwarps, "VKQ_ratio must be <= nwarps.");
// Pad internal representation of KQ, KQV to reduce shared memory bank conflicts:
constexpr int D_padded = D + 8;
constexpr int kqs_padded = FATTN_KQ_STRIDE + 8;
constexpr int kqar = sizeof(KQ_acc_t)/sizeof(half);
ggml_cuda_pdl_sync();
const int sequence = blockIdx.z / ne02;
const int head = blockIdx.z - sequence*ne02;
const int gqa_ratio = ne02 / ne12; // With grouped query attention there are > 1 Q matrices per K, V matrix.
const float * Q_f = (const float *) (Q + nb03* sequence + nb02* head + nb01*ic0);
const half * K_h = (const half *) (K + nb13* sequence + nb12*(head / gqa_ratio));
const half * V_h = (const half *) (V + nb13* sequence + nb12*(head / gqa_ratio)); // K and V have same shape
const half * maskh = (const half *) (mask + nb33*(sequence % ne33) + nb31*ic0);
const half2 * mask2 = (const half2 *) maskh;
const float * sinksf = (const float *) sinks;
const int stride_Q = nb01 / sizeof(float);
const int stride_KV = nb11 / sizeof(half);
const float slopef = get_alibi_slope(max_bias, head, n_head_log2, m0, m1);
const half slopeh = __float2half(slopef);
const half2 slope2 = make_half2(slopef, slopef);
const half2 logit_softcap_2 = make_half2(logit_softcap, logit_softcap);
frag_b Q_b[D/16][ncols/frag_n];
// A single buffer for temporarily holding tiles of KQ and VKQ parts:
constexpr int mem_KQ = ncols*kqs_padded*kqar;
constexpr int mem_VKQ_parts = VKQ_ratio*ncols*D_padded;
__shared__ half KQ[mem_KQ >= mem_VKQ_parts ? mem_KQ : mem_VKQ_parts];
float * KQ_f = (float *) KQ;
half2 * KQ2 = (half2 *) KQ;
float KQ_rowsum_f[ncols/nwarps] = {0.0f};
float KQ_max_f[ncols/nwarps];
float KQ_max_scale_f[ncols/nwarps] = {0.0f};
#pragma unroll
for (int j = 0; j < ncols/nwarps; ++j) {
KQ_max_f[j] = -FLT_MAX/2.0f;
}
half2 KQ_rowsum_h2[ncols/nwarps] = {{0.0f, 0.0f}};
half2 KQ_max_h2[ncols/nwarps];
half2 KQ_max_scale_h2[ncols/nwarps] = {{0.0f, 0.0f}};
#pragma unroll
for (int j = 0; j < ncols/nwarps; ++j) {
KQ_max_h2[j] = make_half2(-HALF_MAX_HALF, -HALF_MAX_HALF);
}
__shared__ half VKQ[ncols*D_padded]; // Accumulator for final VKQ slice.
half2 * VKQ2 = (half2 *) VKQ;
#if defined(GGML_USE_HIP) && HIP_VERSION >= 60500000
const _Float16 * K_h_f16 = reinterpret_cast<const _Float16 *>(K_h);
const _Float16 * V_h_f16 = reinterpret_cast<const _Float16 *>(V_h);
_Float16 * KQ_f16 = reinterpret_cast<_Float16 *>(KQ);
_Float16 * VKQ_f16 = reinterpret_cast<_Float16 *>(VKQ);
#else
const half * K_h_f16 = K_h;
const half * V_h_f16 = V_h;
half * KQ_f16 = KQ;
half * VKQ_f16 = VKQ;
#endif
#pragma unroll
for (int j0 = 0; j0 < ncols; j0 += nwarps) {
const int j = j0 + threadIdx.y;
#pragma unroll
for (int i0 = 0; i0 < D/2; i0 += warp_size) {
const int i = i0 + threadIdx.x;
if (i0 + warp_size > D/2 && i >= D/2) {
break;
}
VKQ2[j*(D_padded/2) + i] = make_half2(0.0f, 0.0f);
}
}
// Convert Q to half and apply scale, temporarily store in KQ:
#pragma unroll
for (int j0 = 0; j0 < ncols; j0 += nwarps) {
const int j = j0 + threadIdx.y;
#pragma unroll
for (int i0 = 0; i0 < D; i0 += warp_size) {
const int i = i0 + threadIdx.x;
if (i0 + warp_size > D && i >= D) {
break;
}
KQ[j*D_padded + i] = ic0 + j < int(ne01.z) ? Q_f[j*stride_Q + i] * scale : 0.0f;
}
}
__syncthreads();
// Load Q into tensor core fragments/registers since it will be used frequently:
#pragma unroll
for (int i0 = 0; i0 < D; i0 += 16) {
#pragma unroll
for (int j0 = 0; j0 < ncols; j0 += frag_n) {
wmma::load_matrix_sync(Q_b[i0/16][j0/frag_n], KQ_f16 + j0*D_padded + i0, D_padded);
}
}
__syncthreads();
// Iterate over ne11 == previous tokens:
const int k_VKQ_max = KV_max ? KV_max[sequence*gridDim.x + blockIdx.x] : ne11;
for (int k_VKQ_0 = blockIdx.y*FATTN_KQ_STRIDE; k_VKQ_0 < k_VKQ_max; k_VKQ_0 += gridDim.y*FATTN_KQ_STRIDE) {
// Calculate tile of KQ:
#pragma unroll
for (int i_KQ_0 = 0; i_KQ_0 < FATTN_KQ_STRIDE; i_KQ_0 += KQ_stride_tc) {
frag_c_KQ KQ_c[ncols/frag_n];
#pragma unroll
for (int j = 0; j < ncols/frag_n; ++j) {
wmma::fill_fragment(KQ_c[j], static_cast<KQ_acc_t>(0.0f));
}
#pragma unroll
for (int k_KQ_0 = 0; k_KQ_0 < D; k_KQ_0 += 16) {
frag_a_K K_a;
wmma::load_matrix_sync(K_a, K_h_f16 + int64_t(k_VKQ_0 + i_KQ_0 + frag_m*threadIdx.y)*stride_KV + k_KQ_0, stride_KV);
#pragma unroll
for (int j = 0; j < ncols/frag_n; ++j) {
wmma::mma_sync(KQ_c[j], K_a, Q_b[k_KQ_0/16][j], KQ_c[j]);
}
}
#pragma unroll
for (int j0 = 0; j0 < ncols; j0 += frag_n) {
wmma::store_matrix_sync((KQ_acc_t *) KQ + j0*kqs_padded + i_KQ_0 + frag_m*threadIdx.y, KQ_c[j0/frag_n], kqs_padded, wmma::mem_col_major);
}
}
__syncthreads();
// Calculate softmax for each KQ column using the current max. value.
// The divisor is stored in KQ_rowsum and will be applied at the end.
#pragma unroll
for (int j0 = 0; j0 < ncols; j0 += nwarps) {
const int j = j0 + threadIdx.y;
if (std::is_same<KQ_acc_t, float>::value) {
float KQ_f_tmp[FATTN_KQ_STRIDE / warp_size];
#pragma unroll
for (int k0 = 0; k0 < FATTN_KQ_STRIDE; k0 += warp_size) {
const int k = k0 + threadIdx.x;
KQ_f_tmp[k0/warp_size] = KQ_f[j*kqs_padded + k];
if (use_logit_softcap) {
KQ_f_tmp[k0/warp_size] = logit_softcap*tanhf(KQ_f_tmp[k0/warp_size]);
}
}
float KQ_max_new = KQ_max_f[j0/nwarps];
#pragma unroll
for (int k0 = 0; k0 < FATTN_KQ_STRIDE; k0 += warp_size) {
const int k = k0 + threadIdx.x;
KQ_f_tmp[k0/warp_size] += mask && ic0 + j < int(ne01.z) ?
__half2float(slopeh*maskh[j*(nb31/sizeof(half)) + k_VKQ_0 + k]) : 0.0f;
KQ_max_new = max(KQ_max_new, KQ_f_tmp[k0/warp_size] + FATTN_KQ_MAX_OFFSET);
}
KQ_max_new = warp_reduce_max<warp_size>(KQ_max_new);
const float diff = KQ_max_f[j0/nwarps] - KQ_max_new;
KQ_max_scale_f[j0/nwarps] = expf(diff);
if (diff <= SOFTMAX_FTZ_THRESHOLD) {
KQ_max_scale_f[j0/nwarps] = 0.0f;
}
KQ_max_f[j0/nwarps] = KQ_max_new;
float KQ_rowsum_add = 0.0f;
#pragma unroll
for (int k0 = 0; k0 < FATTN_KQ_STRIDE; k0 += warp_size) {
const int k = k0 + threadIdx.x;
const float diff = KQ_f_tmp[k0/warp_size] - KQ_max_f[j0/nwarps];
KQ_f_tmp[k0/warp_size] = expf(diff);
if (diff <= SOFTMAX_FTZ_THRESHOLD) {
KQ_f_tmp[k0/warp_size] = 0.0f;
}
KQ_rowsum_add += KQ_f_tmp[k0/warp_size];
KQ[j*(kqar*kqs_padded) + k] = KQ_f_tmp[k0/warp_size];
}
KQ_rowsum_add = warp_reduce_sum<warp_size>(KQ_rowsum_add);
// Scale previous KQ_rowsum to account for a potential increase in KQ_max:
KQ_rowsum_f[j0/nwarps] = KQ_max_scale_f[j0/nwarps]*KQ_rowsum_f[j0/nwarps] + KQ_rowsum_add;
} else {
half2 KQ2_tmp[FATTN_KQ_STRIDE/(2*warp_size)];
#pragma unroll
for (int k0 = 0; k0 < FATTN_KQ_STRIDE/2; k0 += warp_size) {
const int k = k0 + threadIdx.x;
KQ2_tmp[k0/warp_size] = KQ2[j*(kqs_padded/2) + k];
if (use_logit_softcap) {
// There is no dedicated tangens hyperbolicus function for half2.
KQ2_tmp[k0/warp_size] = h2exp(KQ2_tmp[k0/warp_size]*make_half2(2.0f, 2.0f));
KQ2_tmp[k0/warp_size] = (KQ2_tmp[k0/warp_size] - make_half2(1.0f, 1.0f))
/(KQ2_tmp[k0/warp_size] + make_half2(1.0f, 1.0f));
KQ2_tmp[k0/warp_size] *= logit_softcap_2;
}
}
half2 KQ_max_new = KQ_max_h2[j0/nwarps];
#pragma unroll
for (int k0 = 0; k0 < FATTN_KQ_STRIDE/2; k0 += warp_size) {
const int k = k0 + threadIdx.x;
KQ2_tmp[k0/warp_size] += mask && ic0 + j < int(ne01.z) ? slope2*mask2[(j*ne11 + k_VKQ_0)/2 + k] : make_half2(0.0f, 0.0f);
KQ_max_new = ggml_cuda_hmax2(KQ_max_new, KQ2_tmp[k0/warp_size]);
}
KQ_max_new = __half2half2(warp_reduce_max<warp_size>(ggml_cuda_hmax(__low2half(KQ_max_new), __high2half(KQ_max_new))));
const half2 diff = KQ_max_h2[j0/nwarps] - KQ_max_new;
KQ_max_scale_h2[j0/nwarps] = h2exp(diff);
const uint32_t ftz_mask = __hgt2_mask(diff, make_half2(SOFTMAX_FTZ_THRESHOLD, SOFTMAX_FTZ_THRESHOLD));
*((uint32_t *) &KQ_max_scale_h2[j0/nwarps]) &= ftz_mask;
KQ_max_h2[j0/nwarps] = KQ_max_new;
half2 KQ_rowsum_add = make_half2(0.0f, 0.0f);
#pragma unroll
for (int k0 = 0; k0 < FATTN_KQ_STRIDE/2; k0 += warp_size) {
const int k = k0 + threadIdx.x;
const half2 diff = KQ2_tmp[k0/warp_size] - KQ_max_h2[j0/nwarps];
KQ2_tmp[k0/warp_size] = h2exp(diff);
const uint32_t ftz_mask = __hgt2_mask(diff, make_half2(SOFTMAX_FTZ_THRESHOLD, SOFTMAX_FTZ_THRESHOLD));
*((uint32_t *) &KQ2_tmp[k0/warp_size]) &= ftz_mask;
KQ_rowsum_add += KQ2_tmp[k0/warp_size];
KQ2[j*(kqs_padded/2) + k] = KQ2_tmp[k0/warp_size];
}
KQ_rowsum_add = warp_reduce_sum<warp_size>(KQ_rowsum_add);
// Scale previous KQ_rowsum to account for a potential increase in KQ_max:
KQ_rowsum_h2[j0/nwarps] = KQ_max_scale_h2[j0/nwarps]*KQ_rowsum_h2[j0/nwarps] + KQ_rowsum_add;
}
}
__syncthreads();
frag_b KQ_b[FATTN_KQ_STRIDE/(VKQ_ratio*16)][ncols/frag_n];
#pragma unroll
for (int j0 = 0; j0 < ncols; j0 += frag_n) {
#pragma unroll
for (int k0 = 0; k0 < FATTN_KQ_STRIDE; k0 += VKQ_ratio*16) {
const int k = k0 + (threadIdx.y % VKQ_ratio)*16;
wmma::load_matrix_sync(
KQ_b[k0/(VKQ_ratio*16)][j0/frag_n],
KQ_f16 + j0*(kqar*kqs_padded) + k,
kqar*kqs_padded);
}
}
frag_c_VKQ VKQ_c[D/VKQ_stride][ncols/frag_n];
#pragma unroll
for (int i_VKQ_0 = 0; i_VKQ_0 < D; i_VKQ_0 += VKQ_stride) {
#pragma unroll
for (int j = 0; j < ncols/frag_n; ++j) {
wmma::fill_fragment(VKQ_c[i_VKQ_0/VKQ_stride][j], static_cast<half>(0.0f));
}
#pragma unroll
for (int k0 = 0; k0 < FATTN_KQ_STRIDE; k0 += VKQ_ratio*16) {
const int k = k0 + (threadIdx.y % VKQ_ratio)*16;
frag_a_V v_a;
wmma::load_matrix_sync(v_a, V_h_f16 + int64_t(k_VKQ_0 + k)*stride_KV + i_VKQ_0 + frag_m*(threadIdx.y/VKQ_ratio), stride_KV);
#pragma unroll
for (int j = 0; j < ncols/frag_n; ++j) {
wmma::mma_sync(VKQ_c[i_VKQ_0/VKQ_stride][j], v_a, KQ_b[k0/(VKQ_ratio*16)][j], VKQ_c[i_VKQ_0/VKQ_stride][j]);
}
}
}
__syncthreads();
const int offset_k = (threadIdx.y % VKQ_ratio) * (ncols*D_padded);
#pragma unroll
for (int i_KQ_0 = 0; i_KQ_0 < D; i_KQ_0 += VKQ_stride) {
#pragma unroll
for (int j0 = 0; j0 < ncols; j0 += frag_n) {
wmma::store_matrix_sync(
KQ_f16 + offset_k + j0*D_padded + i_KQ_0 + frag_m*(threadIdx.y/VKQ_ratio),
VKQ_c[i_KQ_0/VKQ_stride][j0/frag_n],
D_padded, wmma::mem_col_major);
}
}
__syncthreads();
#pragma unroll
for (int j0 = 0; j0 < ncols; j0 += nwarps) {
const int j = j0 + threadIdx.y;
half2 VKQ_scale;
if (std::is_same<KQ_acc_t, float>::value) {
VKQ_scale = make_half2(KQ_max_scale_f[j0/nwarps], KQ_max_scale_f[j0/nwarps]);
} else {
VKQ_scale = KQ_max_scale_h2[j0/nwarps];
}
#pragma unroll
for (int i0 = 0; i0 < D/2; i0 += warp_size) {
const int i = i0 + threadIdx.x;
if (i0 + warp_size > D/2 && i >= D/2) {
break;
}
half2 VKQ_add = make_half2(0.0f, 0.0f);
#pragma unroll
for (int l = 0; l < VKQ_ratio; ++l) {
VKQ_add += KQ2[l*(ncols*D_padded/2) + j*(D_padded/2) + i];
}
VKQ2[j*(D_padded/2) + i] = VKQ_scale*VKQ2[j*(D_padded/2) + i] + VKQ_add;
}
}
__syncthreads();
}
// Apply attention sinks
if (sinksf && blockIdx.y == 0) {
const float sinkf = sinksf[head];
const half sinkh = __float2half(sinkf);
#pragma unroll
for (int j0 = 0; j0 < ncols; j0 += nwarps) {
const int j = j0 + threadIdx.y;
if (std::is_same<KQ_acc_t, float>::value) {
float kqmax_new = fmaxf(KQ_max_f[j0/nwarps], sinkf);
const float KQ_max_scale = expf(KQ_max_f[j0/nwarps] - kqmax_new);
KQ_max_f[j0/nwarps] = kqmax_new;
KQ_rowsum_f[j0/nwarps] = KQ_rowsum_f[j0/nwarps] * KQ_max_scale + expf(sinkf - KQ_max_f[j0/nwarps]);
const half2 scale_h2 = make_half2(KQ_max_scale, KQ_max_scale);
#pragma unroll
for (int i0 = 0; i0 < D/2; i0 += warp_size) {
const int i = i0 + threadIdx.x;
if (i0 + warp_size > D/2 && i >= D/2) break;
VKQ2[j*(D_padded/2) + i] *= scale_h2;
}
} else {
half kqmax_old = __low2half(KQ_max_h2[j0/nwarps]);
half kqmax_new = fmaxf(kqmax_old, sinkh);
KQ_max_h2[j0/nwarps] = __half2half2(kqmax_new);
const half KQ_max_scale_h = hexp(kqmax_old - kqmax_new);
const half2 KQ_max_scale = __half2half2(KQ_max_scale_h);
KQ_rowsum_h2[j0/nwarps] = KQ_rowsum_h2[j0/nwarps] * KQ_max_scale;
const half val = hexp(sinkh - kqmax_new);
KQ_rowsum_h2[j0/nwarps].x = __hadd(KQ_rowsum_h2[j0/nwarps].x, val);
#pragma unroll
for (int i0 = 0; i0 < D/2; i0 += warp_size) {
const int i = i0 + threadIdx.x;
if (i0 + warp_size > D/2 && i >= D/2) break;
VKQ2[j*(D_padded/2) + i] *= KQ_max_scale;
}
}
}
__syncthreads();
}
#pragma unroll
for (int j0 = 0; j0 < ncols; j0 += nwarps) {
const int j_VKQ = j0 + threadIdx.y;
if (ic0 + j_VKQ >= int(ne01.z)) {
return;
}
float KQ_rowsum_j;
if (std::is_same<KQ_acc_t, float>::value) {
KQ_rowsum_j = KQ_rowsum_f[j0/nwarps];
} else {
KQ_rowsum_j = __low2float(KQ_rowsum_h2[j0/nwarps]) + __high2float(KQ_rowsum_h2[j0/nwarps]);
}
const int j_dst_unrolled = ((sequence*int(ne01.z) + ic0 + j_VKQ)*ne02 + head)*gridDim.y + blockIdx.y;
#pragma unroll
for (int i0 = 0; i0 < D; i0 += warp_size) {
const int i = i0 + threadIdx.x;
if (i0 + warp_size > D && i >= D) {
break;
}
float dst_val = VKQ[j_VKQ*D_padded + i];
if (gridDim.y == 1) {
dst_val /= KQ_rowsum_j;
}
dst[j_dst_unrolled*D + i] = dst_val;
}
if (gridDim.y == 1 || threadIdx.x != 0) {
continue;
}
float2 dst_meta_val;
if (std::is_same<KQ_acc_t, float>::value) {
dst_meta_val.x = KQ_max_f[j0/nwarps];
} else {
dst_meta_val.x = __low2float(KQ_max_h2[j0/nwarps]);
}
dst_meta_val.y = KQ_rowsum_j;
dst_meta[j_dst_unrolled] = dst_meta_val;
}
#else
GGML_UNUSED_VARS(Q_ptr, K_ptr, V_ptr, mask_ptr, sinks_ptr, KV_max_ptr, dst_ptr, dst_meta_ptr, scale,
max_bias, m0, m1, n_head_log2, logit_softcap,
ne00, ne01, ne02, ne03,
nb01, nb02, nb03,
ne10, ne11, ne12, ne13,
nb11, nb12, nb13,
nb21, nb22, nb23,
ne31, ne32, ne33,
nb31, nb32, nb33);
NO_DEVICE_CODE;
#endif // defined(FLASH_ATTN_AVAILABLE) && (defined(GGML_HIP_ROCWMMA_FATTN) && defined(GGML_USE_WMMA_FATTN))
}
constexpr int get_max_power_of_2(int x) {
return x % 2 == 0 ? 2*get_max_power_of_2(x/2) : 1;
}
static_assert(get_max_power_of_2(1) == 1, "Test failed.");
static_assert(get_max_power_of_2(2) == 2, "Test failed.");
static_assert(get_max_power_of_2(4) == 4, "Test failed.");
static_assert(get_max_power_of_2(6) == 2, "Test failed.");
// Number of VKQ rows calculated in parallel:
constexpr int get_VKQ_stride(int D, int nwarps, int frag_m) {
return (get_max_power_of_2(D/frag_m) < nwarps ? get_max_power_of_2(D/frag_m) : nwarps)*frag_m;
}
static_assert(get_VKQ_stride(128, 1, 32) == 32, "Test failed.");
static_assert(get_VKQ_stride(128, 2, 32) == 64, "Test failed.");
static_assert(get_VKQ_stride(128, 4, 32) == 128, "Test failed.");
static_assert(get_VKQ_stride( 64, 1, 32) == 32, "Test failed.");
static_assert(get_VKQ_stride( 64, 2, 32) == 64, "Test failed.");
static_assert(get_VKQ_stride( 64, 4, 32) == 64, "Test failed.");
static_assert(get_VKQ_stride( 80, 1, 16) == 16, "Test failed.");
static_assert(get_VKQ_stride( 80, 2, 16) == 16, "Test failed.");
static_assert(get_VKQ_stride( 80, 4, 16) == 16, "Test failed.");
template <int D, int cols_per_block, typename KQ_acc_t>
void ggml_cuda_flash_attn_ext_wmma_f16_case(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
const ggml_tensor * KQV = dst;
constexpr int nwarps = 4;
constexpr int frag_m = cols_per_block == 8 && D % 32 == 0 ? 32 : 16;
const int warp_size = ggml_cuda_info().devices[ggml_cuda_get_device()].warp_size;
float logit_softcap;
memcpy(&logit_softcap, (const float *) KQV->op_params + 2, sizeof(float));
fattn_kernel_t fattn_kernel;
if (logit_softcap == 0.0f) {
constexpr bool use_logit_softcap = false;
fattn_kernel = flash_attn_ext_f16<
D, cols_per_block, nwarps, get_VKQ_stride(D, nwarps, frag_m), KQ_acc_t, use_logit_softcap>;
} else {
constexpr bool use_logit_softcap = true;
fattn_kernel = flash_attn_ext_f16<
D, cols_per_block, nwarps, get_VKQ_stride(D, nwarps, frag_m), KQ_acc_t, use_logit_softcap>;
}
launch_fattn<D, cols_per_block, 1>(ctx, dst, fattn_kernel, nwarps, 0, FATTN_KQ_STRIDE, true, true, false, warp_size);
}
void ggml_cuda_flash_attn_ext_wmma_f16(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
const ggml_tensor * KQV = dst;
const ggml_tensor * Q = dst->src[0];
const enum ggml_prec prec = ggml_flash_attn_ext_get_prec(KQV);
const int warp_size = ggml_cuda_info().devices[ctx.device].warp_size;
if (prec != GGML_PREC_DEFAULT) {
if (Q->ne[1] <= 32 || Q->ne[0] > 128) {
constexpr int cols_per_block = 16;
switch (Q->ne[0]) {
case 64:
ggml_cuda_flash_attn_ext_wmma_f16_case< 64, cols_per_block, float>(ctx, dst);
break;
case 80:
ggml_cuda_flash_attn_ext_wmma_f16_case< 80, cols_per_block, float>(ctx, dst);
break;
case 96:
ggml_cuda_flash_attn_ext_wmma_f16_case< 96, cols_per_block, float>(ctx, dst);
break;
case 112:
ggml_cuda_flash_attn_ext_wmma_f16_case<112, cols_per_block, float>(ctx, dst);
break;
case 128:
ggml_cuda_flash_attn_ext_wmma_f16_case<128, cols_per_block, float>(ctx, dst);
break;
case 256:
ggml_cuda_flash_attn_ext_wmma_f16_case<256, cols_per_block, float>(ctx, dst);
break;
default:
GGML_ABORT("fatal error");
break;
}
} else {
constexpr int cols_per_block = 32;
switch (Q->ne[0]) {
case 64:
ggml_cuda_flash_attn_ext_wmma_f16_case< 64, cols_per_block, float>(ctx, dst);
break;
case 80:
ggml_cuda_flash_attn_ext_wmma_f16_case< 80, cols_per_block, float>(ctx, dst);
break;
case 96:
ggml_cuda_flash_attn_ext_wmma_f16_case< 96, cols_per_block, float>(ctx, dst);
break;
case 112:
ggml_cuda_flash_attn_ext_wmma_f16_case<112, cols_per_block, float>(ctx, dst);
break;
case 128:
ggml_cuda_flash_attn_ext_wmma_f16_case<128, cols_per_block, float>(ctx, dst);
break;
// case 256:
// ggml_cuda_flash_attn_ext_wmma_f16_case<256, cols_per_block, float>(ctx, dst);
// break;
default:
GGML_ABORT("fatal error");
break;
}
}
return;
}
#if !defined(GGML_USE_HIP)
if (Q->ne[1] <= 8 && Q->ne[0] % warp_size == 0) {
constexpr int cols_per_block = 8;
switch (Q->ne[0]) {
case 64:
ggml_cuda_flash_attn_ext_wmma_f16_case< 64, cols_per_block, half>(ctx, dst);
break;
case 96:
ggml_cuda_flash_attn_ext_wmma_f16_case< 96, cols_per_block, half>(ctx, dst);
break;
case 128:
ggml_cuda_flash_attn_ext_wmma_f16_case<128, cols_per_block, half>(ctx, dst);
break;
case 256:
ggml_cuda_flash_attn_ext_wmma_f16_case<256, cols_per_block, half>(ctx, dst);
break;
default:
GGML_ABORT("fatal error");
break;
}
return;
}
#endif // !defined(GGML_USE_HIP)
if (Q->ne[1] <= 32) {
constexpr int cols_per_block = 16;
switch (Q->ne[0]) {
case 64:
ggml_cuda_flash_attn_ext_wmma_f16_case< 64, cols_per_block, half>(ctx, dst);
break;
case 80:
ggml_cuda_flash_attn_ext_wmma_f16_case< 80, cols_per_block, half>(ctx, dst);
break;
case 96:
ggml_cuda_flash_attn_ext_wmma_f16_case< 96, cols_per_block, half>(ctx, dst);
break;
case 112:
ggml_cuda_flash_attn_ext_wmma_f16_case<112, cols_per_block, half>(ctx, dst);
break;
case 128:
ggml_cuda_flash_attn_ext_wmma_f16_case<128, cols_per_block, half>(ctx, dst);
break;
case 256:
ggml_cuda_flash_attn_ext_wmma_f16_case<256, cols_per_block, half>(ctx, dst);
break;
default:
GGML_ABORT("fatal error");
break;
}
return;
}
constexpr int cols_per_block = 32;
switch (Q->ne[0]) {
case 64:
ggml_cuda_flash_attn_ext_wmma_f16_case< 64, cols_per_block, half>(ctx, dst);
break;
case 80:
ggml_cuda_flash_attn_ext_wmma_f16_case< 80, cols_per_block, half>(ctx, dst);
break;
case 96:
ggml_cuda_flash_attn_ext_wmma_f16_case< 96, cols_per_block, half>(ctx, dst);
break;
case 112:
ggml_cuda_flash_attn_ext_wmma_f16_case<112, cols_per_block, half>(ctx, dst);
break;
case 128:
ggml_cuda_flash_attn_ext_wmma_f16_case<128, cols_per_block, half>(ctx, dst);
break;
case 256:
ggml_cuda_flash_attn_ext_wmma_f16_case<256, cols_per_block, half>(ctx, dst);
break;
default:
GGML_ABORT("fatal error");
break;
}
}

51
ggml/src/ggml-cuda/fattn-wmma-f16.cuh
View File

@@ -1,51 +0,0 @@
#pragma once
#include "common.cuh"
#if defined(GGML_USE_MUSA)
#define GGML_USE_WMMA_FATTN
#endif // defined(GGML_USE_MUSA)
#if defined(GGML_HIP_ROCWMMA_FATTN)
#if defined(CDNA) && (ROCWMMA_VERSION_MAJOR < 2 || ROCWMMA_VERSION_MINOR > 0 || ROCWMMA_VERSION_PATCH > 0)
#define GGML_USE_WMMA_FATTN
#elif defined(CDNA)
#warning "rocwmma fattn on CDNA is broken on rocwmma v2.0.0, expect degraded performance"
#endif // defined(CDNA) && (ROCWMMA_VERSION_MAJOR < 2 || ROCWMMA_VERSION_MINOR > 0 || ROCWMMA_VERSION_PATCH > 0)
#if defined(RDNA3)
#define GGML_USE_WMMA_FATTN
#endif // defined(RDNA3)
#if defined(RDNA4) && ROCWMMA_VERSION_MAJOR > 1
#define GGML_USE_WMMA_FATTN
#elif defined(RDNA4)
#warning "rocwmma fattn is not supported on RDNA4 on rocwmma < v2.0.0, expect degraded performance"
#endif // defined(RDNA4) && ROCWMMA_VERSION_MAJOR > 1
#endif // defined(GGML_HIP_ROCWMMA_FATTN)
// WMMA flash attention requires FP16 matrix instructions to be available for ggml code.
static bool ggml_cuda_should_use_wmma_fattn(const int cc) {
#if defined(GGML_USE_HIP) && !defined(GGML_HIP_ROCWMMA_FATTN)
return false;
#else
if ((GGML_CUDA_CC_IS_NVIDIA(cc) && ggml_cuda_highest_compiled_arch(cc) == GGML_CUDA_CC_VOLTA) ||
GGML_CUDA_CC_IS_RDNA3(cc) || GGML_CUDA_CC_IS_MTHREADS(cc)) {
return true;
} else if (GGML_CUDA_CC_IS_CDNA(cc)){
#if defined(GGML_HIP_ROCWMMA_FATTN) && (ROCWMMA_VERSION_MAJOR < 2 || ROCWMMA_VERSION_MINOR > 0 || ROCWMMA_VERSION_PATCH > 0)
return true;
#else
return false;
#endif // defined(GGML_HIP_ROCWMMA_FATTN) (ROCWMMA_VERSION_MAJOR < 2 || ROCWMMA_VERSION_MINOR > 0 || ROCWMMA_VERSION_PATCH > 0)
} else if (GGML_CUDA_CC_IS_RDNA4(cc)) {
#if defined(GGML_HIP_ROCWMMA_FATTN) && ROCWMMA_VERSION_MAJOR > 1
return true;
#else
return false;
#endif // defined(GGML_HIP_ROCWMMA_FATTN) && ROCWMMA_VERSION_MAJOR > 1
} else {
return false;
}
#endif // defined(GGML_USE_HIP) && !defined(GGML_HIP_ROCWMMA_FATTN)
}
void ggml_cuda_flash_attn_ext_wmma_f16(ggml_backend_cuda_context & ctx, ggml_tensor * dst);

22
ggml/src/ggml-cuda/fattn.cu
View File

@@ -3,7 +3,6 @@
#include "fattn-mma-f16.cuh"
#include "fattn-tile.cuh"
#include "fattn-vec.cuh"
#include "fattn-wmma-f16.cuh"
#include "fattn.cuh"
template <int DKQ, int DV, int ncols2>
@@ -330,11 +329,10 @@ static void ggml_cuda_flash_attn_ext_vec(ggml_backend_cuda_context & ctx, ggml_t
// Best FlashAttention kernel for a specific GPU:
enum best_fattn_kernel {
BEST_FATTN_KERNEL_NONE = 0,
BEST_FATTN_KERNEL_TILE = 200,
BEST_FATTN_KERNEL_VEC = 100,
BEST_FATTN_KERNEL_WMMA_F16 = 300,
BEST_FATTN_KERNEL_MMA_F16 = 400,
BEST_FATTN_KERNEL_NONE = 0,
BEST_FATTN_KERNEL_TILE = 200,
BEST_FATTN_KERNEL_VEC = 100,
BEST_FATTN_KERNEL_MMA_F16 = 400,
};
static bool ggml_cuda_fattn_kv_type_supported(ggml_type type) {
@@ -500,14 +498,6 @@ static best_fattn_kernel ggml_cuda_get_best_fattn_kernel(const int device, const
return BEST_FATTN_KERNEL_MMA_F16;
}
// Use the WMMA kernel if possible:
if (ggml_cuda_should_use_wmma_fattn(cc) && K->ne[1] % FATTN_KQ_STRIDE == 0 && Q->ne[0] != 40 && Q->ne[0] != 72 && Q->ne[0] != 192 && Q->ne[0] != 512 && Q->ne[0] != 576) {
if (can_use_vector_kernel && Q->ne[1] <= 2) {
return BEST_FATTN_KERNEL_VEC;
}
return BEST_FATTN_KERNEL_WMMA_F16;
}
// AMD MFMA needs a certain minimum batch size to outscale the tile kernel for large head sizes.
if ((amd_mfma_available(cc) && Q->ne[0] <= 256) && Q->ne[0] != 40 && Q->ne[0] != 72) {
if ((Q->ne[0] <= 64 && Q->ne[1] * gqa_ratio_eff > 8)) {
@@ -559,7 +549,6 @@ size_t ggml_cuda_flash_attn_ext_get_alloc_size(int device, const ggml_tensor * d
switch (kernel) {
case BEST_FATTN_KERNEL_TILE:
case BEST_FATTN_KERNEL_WMMA_F16:
case BEST_FATTN_KERNEL_MMA_F16:
need_f16_K = true;
need_f16_V = true;
@@ -589,9 +578,6 @@ void ggml_cuda_flash_attn_ext(ggml_backend_cuda_context & ctx, ggml_tensor * dst
case BEST_FATTN_KERNEL_VEC:
ggml_cuda_flash_attn_ext_vec(ctx, dst);
break;
case BEST_FATTN_KERNEL_WMMA_F16:
ggml_cuda_flash_attn_ext_wmma_f16(ctx, dst);
break;
case BEST_FATTN_KERNEL_MMA_F16:
ggml_cuda_flash_attn_ext_mma_f16(ctx, dst);
break;

4
ggml/src/ggml-cuda/vendors/hip.h vendored
View File

@@ -6,10 +6,6 @@
#include <hip/hip_fp16.h>
#include <hip/hip_bf16.h>
#if defined(GGML_HIP_ROCWMMA_FATTN)
#include <rocwmma/rocwmma-version.hpp>
#endif // defined(GGML_HIP_ROCWMMA_FATTN)
#ifdef GGML_USE_NCCL
#include <rccl/rccl.h>
#endif // GGML_USE_NCCL

4
ggml/src/ggml-hip/CMakeLists.txt
View File

@@ -114,10 +114,6 @@ if (GGML_HIP_NO_VMM)
add_compile_definitions(GGML_HIP_NO_VMM)
endif()
if (GGML_HIP_ROCWMMA_FATTN)
add_compile_definitions(GGML_HIP_ROCWMMA_FATTN)
endif()
if (NOT GGML_HIP_MMQ_MFMA)
add_compile_definitions(GGML_HIP_NO_MMQ_MFMA)
endif()