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

hexagon: partial im2col support (#26007)

Browse Source 
* hexagon: add IM2COL op

Add Hexagon IM2COL support targeting only patch-embedding convolutions.

* hexagon: im2col refactor and cleanup

* hex-im2col: instrument and update im2col.

* hex-im2col: add local htp_vtcm_layout computation.
This commit is contained in:
Todor Boinovski
2026-07-25 15:47:29 -07:00
committed by GitHub
parent c812c543f8
commit 355303edab
6 changed files with 346 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
@@ -3281,6 +3281,35 @@ static bool ggml_hexagon_supported_ssm_conv(const struct ggml_hexagon_session *
GGML_UNUSED(sess);
}
static bool ggml_hexagon_supported_im2col(const struct ggml_hexagon_session * sess, const struct ggml_tensor * op) {
const struct ggml_tensor * src1 = op->src[1];
const struct ggml_tensor * dst = op;
const bool is_2D = ((const int32_t *) op->op_params)[6] == 1;
if (!is_2D) {
return false;
}
// For now support F32->F32 and F32->F16 only.
if (src1->type != GGML_TYPE_F32 || (dst->type != GGML_TYPE_F16 && dst->type != GGML_TYPE_F32)) {
return false;
}
if (!ggml_is_contiguous(src1) || !ggml_is_contiguous(dst)) {
return false;
}
// For now keep padded OPs on CPU. Will revisit once we expand coverage past patch-embed OPs.
const int32_t p0 = ((const int32_t *) op->op_params)[2];
const int32_t p1 = ((const int32_t *) op->op_params)[3];
if (p0 != 0 || p1 != 0) {
return false;
}
GGML_UNUSED(sess);
return true;
}
static bool ggml_hexagon_supported_pad(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;
@@ -3430,6 +3459,7 @@ static htp_op_code op_remap_to_htp(const ggml_tensor * t) {
case GGML_OP_SOLVE_TRI: return HTP_OP_SOLVE_TRI;
case GGML_OP_TRI: return HTP_OP_TRI;
case GGML_OP_PAD: return HTP_OP_PAD;
case GGML_OP_IM2COL: return HTP_OP_IM2COL;
case GGML_OP_UNARY:
switch (ggml_get_unary_op(t)) {
@@ -4152,6 +4182,10 @@ 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_IM2COL:
supp = ggml_hexagon_supported_im2col(sess, op);
break;
case GGML_OP_GATED_DELTA_NET:
supp = ggml_hexagon_supported_gated_delta_net(sess, op);
break;