DeepseekV4: Add fused hyper-connection ops (#25585)
* dsv4 hc-ops * add missing files; * add cparams * update rpc version * address review comments * address review comments
This commit is contained in:
@@ -58,6 +58,7 @@
|
||||
#include "ggml-cuda/wkv.cuh"
|
||||
#include "ggml-cuda/gla.cuh"
|
||||
#include "ggml-cuda/gated_delta_net.cuh"
|
||||
#include "ggml-cuda/dsv4-hc.cuh"
|
||||
#include "ggml-cuda/set.cuh"
|
||||
#include "ggml-cuda/set-rows.cuh"
|
||||
#include "ggml-cuda/pad_reflect_1d.cuh"
|
||||
@@ -2319,6 +2320,15 @@ static bool ggml_cuda_compute_forward(ggml_backend_cuda_context & ctx, struct gg
|
||||
case GGML_OP_GATED_DELTA_NET:
|
||||
ggml_cuda_op_gated_delta_net(ctx, dst);
|
||||
break;
|
||||
case GGML_OP_DSV4_HC_COMB:
|
||||
ggml_cuda_op_dsv4_hc_comb(ctx, dst);
|
||||
break;
|
||||
case GGML_OP_DSV4_HC_PRE:
|
||||
ggml_cuda_op_dsv4_hc_pre(ctx, dst);
|
||||
break;
|
||||
case GGML_OP_DSV4_HC_POST:
|
||||
ggml_cuda_op_dsv4_hc_post(ctx, dst);
|
||||
break;
|
||||
case GGML_OP_RWKV_WKV7:
|
||||
ggml_cuda_op_rwkv_wkv7(ctx, dst);
|
||||
break;
|
||||
@@ -5088,6 +5098,16 @@ static bool ggml_backend_cuda_device_supports_op(ggml_backend_dev_t dev, const g
|
||||
#else
|
||||
return true;
|
||||
#endif // GGML_USE_MUSA
|
||||
case GGML_OP_DSV4_HC_COMB:
|
||||
return op->src[0]->type == GGML_TYPE_F32 && op->src[1]->type == GGML_TYPE_F32 &&
|
||||
op->src[2]->type == GGML_TYPE_F32 && op->type == GGML_TYPE_F32;
|
||||
case GGML_OP_DSV4_HC_PRE:
|
||||
return op->src[0]->type == GGML_TYPE_F32 && op->src[1]->type == GGML_TYPE_F32 &&
|
||||
op->type == GGML_TYPE_F32;
|
||||
case GGML_OP_DSV4_HC_POST:
|
||||
return op->src[0]->type == GGML_TYPE_F32 && op->src[1]->type == GGML_TYPE_F32 &&
|
||||
op->src[2]->type == GGML_TYPE_F32 && op->src[3]->type == GGML_TYPE_F32 &&
|
||||
op->type == GGML_TYPE_F32;
|
||||
case GGML_OP_FLASH_ATTN_EXT:
|
||||
return ggml_cuda_flash_attn_ext_supported(dev_ctx->device, op);
|
||||
case GGML_OP_CROSS_ENTROPY_LOSS:
|
||||
|
||||
Reference in New Issue
Block a user