Trivikram Reddy bcaf449826 hexagon: eliminate scalar VTCM loads via HVX splat helpers (llama/22993) ...

* hexagon: add hvx_vec_repl helpers and use those for splat-from-vtcm usecase

* hmx-mm: optimize per-group scale handling

* hmx-fa: optimize slope load from vtcm

* hmx-fa: use aligned access where possible in hmx-utils

* hexagon: add hvx_vec_repl_2x_f16 helper and consolidate repl helpers

---------

Co-authored-by: Max Krasnyansky <maxk@qti.qualcomm.com>

2026-05-14 21:26:48 +03:00

..

cmake

cmake : add FindNCCL.cmake (ggml/0)

2026-05-02 15:02:42 +03:00

include

CUDA: lower-case PCI bus id, standardize for ggml (llama/22820)

2026-05-14 21:26:48 +03:00

src

hexagon: eliminate scalar VTCM loads via HVX splat helpers (llama/22993)

2026-05-14 21:26:48 +03:00

.gitignore

whisper : reorganize source code + improve CMake (#2256)

2024-06-26 19:34:09 +03:00

CMakeLists.txt

ggml: install ggml.pc in <libdir>/pkgconfig (ggml/1480)

2026-05-14 21:26:48 +03:00