Kawrakow 0386bfb19b Perhaps slightly faster trellis quants (#541) ...

* This seems slightly faster for IQ2_KT, IQ3_KT TG

* This looks better for iq4_kt TG

* WIP

* Cleanup

* With fancy simd also set func16

* Enable next_128() also on AVX2

Despite having just 16 vector registers it is still faster.

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>

2025-06-21 16:32:16 +02:00

..

cmake

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

include

Fix non rpc build error (#506)

2025-06-08 17:27:00 +03:00

src

Perhaps slightly faster trellis quants (#541)

2025-06-21 16:32:16 +02:00

.gitignore

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

CMakeLists.txt

Better strategy for GPU offload (#520)

2025-06-12 19:25:11 +03:00