]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
hexagon: add HTP kernel for GGML_OP_GATED_DELTA_NET (#22837)
authorYanzhao Wang <redacted>
Sat, 9 May 2026 00:12:04 +0000 (17:12 -0700)
committerGitHub <redacted>
Sat, 9 May 2026 00:12:04 +0000 (17:12 -0700)
commit66001722aa0c79ef12505488eb2d15400c3e8569
treefea6334850e6ca9a6157acdc67b21d11aaf4204b
parentc5703e03a591766418a50026daa14c35fb542aa8
hexagon: add HTP kernel for GGML_OP_GATED_DELTA_NET (#22837)

Implement the Gated Delta Net recurrence on HVX with:
- 4-row fused kernels for PP (prompt processing) path
- 8-row fused kernels for TG (token generation) path, reducing
  K/Q/gate vector reload overhead by 2x
- Separate PP/TG thread functions for I-cache isolation
- VTCM state scratchpad with DMA in/out for TG single-cycle access
- Vectorized gate exp via hvx_exp_f32
ggml/src/ggml-hexagon/ggml-hexagon.cpp
ggml/src/ggml-hexagon/htp/CMakeLists.txt
ggml/src/ggml-hexagon/htp/gated-delta-net-ops.c [new file with mode: 0644]
ggml/src/ggml-hexagon/htp/htp-ctx.h
ggml/src/ggml-hexagon/htp/htp-ops.h
ggml/src/ggml-hexagon/htp/main.c