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

hexagon: add f32 ssm_conv op (#20122)

Browse Source 
* hexagon: add ssm_conv op

* hexagon: hvx kernel is functional

* hexagon: improvements to ssm-conv hvx kernel

* hexagon: added dma to ssm-conv hvx kernel

* hexagon: ssm-conv dynamically compute gather scratchpad

* hex-ssm-conv: add local context and fix various issues (spad indexing, etc)

---------

Co-authored-by: Max Krasnyansky <maxk@qti.qualcomm.com>
This commit is contained in:
Todor Boinovski
2026-03-06 09:59:26 -08:00
committed by GitHub
co-authored by Max Krasnyansky
parent e68f2fb894
commit 34df42f7be
7 changed files with 456 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-hexagon/htp/htp-ops.h
+1 -3
View File
@@ -41,9 +41,6 @@ struct htp_ops_context {
worker_pool_context_t * wpool; // worker pool
uint32_t n_threads; // num threads
uint32_t src0_nrows_per_thread;
uint32_t src1_nrows_per_thread;
uint32_t flags;
};
@@ -61,5 +58,6 @@ int op_set_rows(struct htp_ops_context * octx);
int op_get_rows(struct htp_ops_context * octx);
int op_cpy(struct htp_ops_context * octx);
int op_argsort(struct htp_ops_context * octx);
int op_ssm_conv(struct htp_ops_context * octx);
#endif /* HTP_OPS_H */