llama.cpp

mirrors/llama.cpp

0 Fork 0

mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-10-28 17:56:13 +08:00

Files

T

History

Todor BoinovskiandMax Krasnyansky 797de63b2f hexagon: add support for Q1_0 and Q2_0 (#30122 )

* hexagon: add support for q1_0 quant

* hexagon: enable Q1_0 weights in the 2D HMX MUL_MAT path

* hex-q1: cleanup gates, generalize tiling and remove in-loop divs

* hex-tiling: document tiled formats in developer.md and update htp-tensor.h

* hex-q2: add support for Q2_0

* hex-q2: remove stale asserts and speacial cases

* hex-mm: fix MUL_MAT_NX assumption about square tiling, Q1/Q2 have non-square tiles

* hex-q1/2: minor optimizations (unrolls/un-unrolls/...)

* hex-q1: optimize Q1_0 layout to reduce unpack/vrmpy overhead

* hex-q1/q2_0: further optimize vec_dots

---------

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

2026-10-17 13:36:38 -07:00

snapdragon

hexagon: add support for Q1_0 and Q2_0 (#30122 )

2026-10-17 13:36:38 -07:00

VirtGPU

ggml-virtgpu: Fix some build commands (#20341 )

2026-03-12 15:47:45 +08:00

AOCL.md

BLAS : Document AOCL-BLAS build and label the device AOCL-BLAS (#29640 )

2026-10-01 08:35:01 +03:00

BLIS.md

make : deprecate (#10514 )