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

CUDA/HIP: Fix fattn-vec-* when device warp size is not 32 (#12315)

Browse Source 
When fattn-wmma was ported over to warp64 various bits that also touch fattn-vec where converted to
selectable warp size, however the fattn-vec kernels dont work with 64 wide warps for now, so we need
to avoid launching them with parameters for warp64
This commit is contained in:
uvos
2025-03-12 10:14:11 +01:00
committed by GitHub
parent 7841fc723e
commit 34c961b181
2 changed files with 26 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
ggml/src/ggml-cuda/fattn-wmma-f16.cu
View File

@@ -469,6 +469,7 @@ void ggml_cuda_flash_attn_ext_wmma_f16_case(ggml_backend_cuda_context & ctx, ggm
constexpr int frag_m = cols_per_block == 8 && D % 32 == 0 ? 32 : 16;
const int blocks_num_pb1 = ((Q->ne[1] + cols_per_block - 1) / cols_per_block)*Q->ne[2]*Q->ne[3];
const int nsm = ggml_cuda_info().devices[ggml_cuda_get_device()].nsm;
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));
@@ -485,7 +486,7 @@ void ggml_cuda_flash_attn_ext_wmma_f16_case(ggml_backend_cuda_context & ctx, ggm
fattn_kernel = flash_attn_ext_f16<
D, cols_per_block, nwarps, get_VKQ_stride(D, nwarps, frag_m), parallel_blocks, KQ_acc_t, use_logit_softcap>;
}
launch_fattn<D, cols_per_block, 1, parallel_blocks, -1>(ctx, dst, fattn_kernel, nwarps, 0, true, true);
launch_fattn<D, cols_per_block, 1, parallel_blocks, -1>(ctx, dst, fattn_kernel, nwarps, 0, true, true, warp_size);
return;
}
if (2*blocks_num_pb1 < 2*nsm) {
@@ -500,7 +501,7 @@ void ggml_cuda_flash_attn_ext_wmma_f16_case(ggml_backend_cuda_context & ctx, ggm
fattn_kernel = flash_attn_ext_f16<
D, cols_per_block, nwarps, get_VKQ_stride(D, nwarps, frag_m), parallel_blocks, KQ_acc_t, use_logit_softcap>;
}
launch_fattn<D, cols_per_block, 1, parallel_blocks, -1>(ctx, dst, fattn_kernel, nwarps, 0, true, true);
launch_fattn<D, cols_per_block, 1, parallel_blocks, -1>(ctx, dst, fattn_kernel, nwarps, 0, true, true, warp_size);
return;
}
constexpr int parallel_blocks = 1;
@@ -514,7 +515,7 @@ void ggml_cuda_flash_attn_ext_wmma_f16_case(ggml_backend_cuda_context & ctx, ggm
fattn_kernel = flash_attn_ext_f16<
D, cols_per_block, nwarps, get_VKQ_stride(D, nwarps, frag_m), parallel_blocks, KQ_acc_t, use_logit_softcap>;
}
launch_fattn<D, cols_per_block, 1, parallel_blocks, -1>(ctx, dst, fattn_kernel, nwarps, 0, true, true);
launch_fattn<D, cols_per_block, 1, parallel_blocks, -1>(ctx, dst, fattn_kernel, nwarps, 0, true, true, warp_size);
}
void ggml_cuda_flash_attn_ext_wmma_f16(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {