nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 33 Packages Projects Releases Wiki Activity

hexagon : add cumsum op support (#21246)

Browse Source 
* hexagon : add cumsum op support

* hexagon: enable dma for cumsum op

* Fix line-ending

---------

Co-authored-by: Max Krasnyansky <maxk@qti.qualcomm.com>
This commit is contained in:
Todor Boinovski
2026-04-01 17:44:02 -07:00
committed by GitHub
co-authored by Max Krasnyansky
parent c30e012253
commit fbd441c379
6 changed files with 347 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-hexagon/ggml-hexagon.cpp
+34
View File
@@ -2231,6 +2231,22 @@ static bool ggml_hexagon_supported_ssm_conv(const struct ggml_hexagon_session *
return true;
}
static bool ggml_hexagon_supported_cumsum(const struct ggml_hexagon_session * sess, const struct ggml_tensor * op) {
const struct ggml_tensor * src0 = op->src[0];
const struct ggml_tensor * dst = op;
if (src0->type != GGML_TYPE_F32 || dst->type != GGML_TYPE_F32) {
return false;
}
if (!ggml_is_contiguous(src0) || !ggml_is_contiguous(dst)) {
return false;
}
GGML_UNUSED(sess);
return true;
}
enum dspqbuf_type {
DSPQBUF_TYPE_DSP_WRITE_CPU_READ = 0,
DSPQBUF_TYPE_CPU_WRITE_DSP_READ,
@@ -2399,6 +2415,16 @@ static inline size_t init_repeat_req(htp_general_req * req, dspqueue_buffer * bu
return n_bufs;
}
static inline size_t init_cumsum_req(htp_general_req * req, dspqueue_buffer * bufs, const ggml_tensor * t) {
req->op = HTP_OP_CUMSUM;
size_t n_bufs = 0;
n_bufs += htp_req_buff_init(&req->src0, &bufs[n_bufs], t->src[0], DSPQBUF_TYPE_CPU_WRITE_DSP_READ);
n_bufs += htp_req_buff_init(&req->dst, &bufs[n_bufs], t, DSPQBUF_TYPE_DSP_WRITE_CPU_READ);
return n_bufs;
}
static inline size_t init_get_rows_req(htp_general_req * req, dspqueue_buffer * bufs, const ggml_tensor * t) {
req->op = HTP_OP_GET_ROWS;
@@ -2780,6 +2806,10 @@ static ggml_status ggml_backend_hexagon_graph_compute(ggml_backend_t backend, gg
ggml_hexagon_dispatch_op<init_ssm_conv_req>(sess, node, flags);
break;
case GGML_OP_CUMSUM:
ggml_hexagon_dispatch_op<init_cumsum_req>(sess, node, flags);
break;
default:
GGML_ABORT("\nggml-hex: graph-compute %s is not supported\n", ggml_op_desc(node));
}
@@ -3254,6 +3284,10 @@ static bool ggml_backend_hexagon_device_supports_op(ggml_backend_dev_t dev, cons
supp = ggml_hexagon_supported_ssm_conv(sess, op);
break;
case GGML_OP_CUMSUM:
supp = ggml_hexagon_supported_cumsum(sess, op);
break;
default:
break;
}