Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

hexagon: various Op fixes (#17135)

Browse Source 
* hexagon: explicitly check for ops with zero nrows

llm_graph_context::build_inp_out_ids() can generate tensors with zero nrows.
Somehow other backends seems to handle this without obvious explicit checks.
In the hexagon case we need to check explicitly and skip them.

* hexagon: introduce fastdiv, fix test-backend-ops for ADD/SUB/MUL

Co-authored-by: chraac <chraac@gmail.com>

* hexagon: use fastdiv in ADD_ID

* hexagon: use ggml_op_is_empty and ggml_is_empty to check for NOPs

---------

Co-authored-by: chraac <chraac@gmail.com>
This commit is contained in:
Max Krasnyansky
2025-11-11 15:25:04 -08:00
committed by GitHub
co-authored by chraac
parent 7d019cff74
commit c273d75375
5 changed files with 105 additions and 58 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-hexagon/htp/htp-ops.h
+11
View File
@@ -4,6 +4,7 @@
#include "htp-ctx.h"
#include "htp-msg.h"
#include "worker-pool.h"
#include "ops-utils.h"
#include <assert.h>
#include <stdint.h>
@@ -38,6 +39,16 @@ struct htp_ops_context {
uint32_t src0_nrows_per_thread;
uint32_t src1_nrows_per_thread;
struct fastdiv_values src0_div1; // fastdiv values for ne1
struct fastdiv_values src0_div2; // fastdiv values for ne2
struct fastdiv_values src0_div3; // fastdiv values for ne3
struct fastdiv_values src0_div21; // fastdiv values for ne2 * ne1
struct fastdiv_values src1_div1; // fastdiv values for ne1
struct fastdiv_values src1_div2; // fastdiv values for ne2
struct fastdiv_values src1_div3; // fastdiv values for ne3
struct fastdiv_values src1_div21; // fastdiv values for ne2 * ne1
uint32_t flags;
};