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	…
CMakeLists.txt	ggml: install ggml.pc in <libdir>/pkgconfig (ggml/1480)	2026-05-14 21:26:48 +03:00