happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

CANN: add SOFTPLUS unary op support 

Implement GGML_UNARY_OP_SOFTPLUS using aclnnSoftplus with beta=1.0
and threshold=20.0. This enables hybrid models like Qwen3.5 to run
entirely on the CANN backend without graph splitting, which fixes
graph cache instability caused by the backend scheduler fragmenting
the computation graph when SOFTPLUS falls back to CPU.
This commit is contained in:
hipudding 2026-03-28 07:16:07 +00:00
parent 168d05f3d5
commit cb15cdb020
2 changed files with 17 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
ggml/src/ggml-cann/aclnn_ops.h
View File

@ -50,6 +50,7 @@
#include <aclnnop/aclnn_sign.h>
#include <aclnnop/aclnn_silu.h>
#include <aclnnop/aclnn_sin.h>
#include <aclnnop/aclnn_softplus.h>
#include <aclnnop/aclnn_slice.h>
#include <aclnnop/aclnn_sqrt.h>
#include <aclnnop/aclnn_tanh.h>

16
ggml/src/ggml-cann/ggml-cann.cpp
View File

@ -1748,6 +1748,20 @@ static bool ggml_cann_compute_forward(ggml_backend_cann_context & ctx, struct gg
case GGML_UNARY_OP_STEP:
ggml_cann_step(ctx, dst);
break;
case GGML_UNARY_OP_SOFTPLUS:
{
auto lambda = [](ggml_backend_cann_context & ctx, aclTensor * acl_src, aclTensor * acl_dst) {
float beta_val = 1.0f;
float threshold_val = 20.0f;
aclScalar * beta = aclCreateScalar(&beta_val, aclDataType::ACL_FLOAT);
aclScalar * threshold = aclCreateScalar(&threshold_val, aclDataType::ACL_FLOAT);
GGML_CANN_CALL_ACLNN_OP(ctx, Softplus, acl_src, beta, threshold, acl_dst);
aclDestroyScalar(beta);
aclDestroyScalar(threshold);
};
ggml_cann_op_unary(lambda, ctx, dst);
}
break;
default:
return false;
}
@ -2258,6 +2272,7 @@ static enum ggml_status ggml_backend_cann_graph_compute(ggml_backend_t backend,
if (use_cann_graph) {
// If no matching graph is found, the graph needs to be recaptured.
graph_capture_required = !cann_ctx->graph_lru_cache.find_and_move_to_front(cgraph);
if (graph_capture_required) {
// If no matching graph is found, add a new ACL graph.
ggml_cann_graph * new_graph = ggml_cann_graph::create_from_cgraph(cgraph);
@ -2316,6 +2331,7 @@ static bool ggml_backend_cann_supports_op(ggml_backend_dev_t dev, const ggml_ten
case GGML_UNARY_OP_SGN:
case GGML_UNARY_OP_STEP:
case GGML_UNARY_OP_GELU_ERF:
case GGML_UNARY_OP_SOFTPLUS:
return true;
default:
return false;