tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-14 04:17:53 -04:00
Code Issues Packages Projects Releases Wiki Activity

RWKV v6: RWKV_WKV op CUDA implementation (#9454)

Browse Source 
* ggml: CUDA unary op EXP

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* ggml: rwkv_wkv op CUDA impl

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

---------

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
This commit is contained in:
Molly Sophia
2024-09-22 10:29:12 +08:00
committed by GitHub
parent d09770cae7
commit 2a63caaa69
6 changed files with 168 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
ggml/src/ggml-cuda.cu
View File

@@ -34,6 +34,7 @@
#include "ggml-cuda/tsembd.cuh"
#include "ggml-cuda/unary.cuh"
#include "ggml-cuda/upscale.cuh"
#include "ggml-cuda/rwkv-wkv.cuh"
#include <algorithm>
#include <array>
@@ -2243,6 +2244,9 @@ static bool ggml_cuda_compute_forward(ggml_backend_cuda_context & ctx, struct gg
case GGML_UNARY_OP_HARDSWISH:
ggml_cuda_op_hardswish(ctx, dst);
break;
case GGML_UNARY_OP_EXP:
ggml_cuda_op_exp(ctx, dst);
break;
default:
return false;
}
@@ -2345,6 +2349,8 @@ static bool ggml_cuda_compute_forward(ggml_backend_cuda_context & ctx, struct gg
case GGML_OP_CROSS_ENTROPY_LOSS:
ggml_cuda_cross_entropy_loss(ctx, dst);
break;
case GGML_OP_RWKV_WKV:
ggml_cuda_op_rwkv_wkv(ctx, dst);
case GGML_OP_CROSS_ENTROPY_LOSS_BACK:
ggml_cuda_cross_entropy_loss_back(ctx, dst);
break;
@@ -2806,6 +2812,7 @@ GGML_CALL static bool ggml_backend_cuda_supports_op(ggml_backend_t backend, cons
case GGML_UNARY_OP_HARDSWISH:
case GGML_UNARY_OP_GELU_QUICK:
case GGML_UNARY_OP_TANH:
case GGML_UNARY_OP_EXP:
return ggml_is_contiguous(op->src[0]);
default:
return false;
@@ -2967,6 +2974,7 @@ GGML_CALL static bool ggml_backend_cuda_supports_op(ggml_backend_t backend, cons
case GGML_OP_ARANGE:
case GGML_OP_TIMESTEP_EMBEDDING:
case GGML_OP_LEAKY_RELU:
case GGML_OP_RWKV_WKV:
return true;
case GGML_OP_FLASH_ATTN_EXT:
#if defined(GGML_USE_HIPBLAS) && defined(__HIP_PLATFORM_AMD__)