Kawrakow 97c34f4056 Faster prompt processing for IQ2_KS, IQ2_K, IQ2_K_R4 (#593) ...

* cuda: faster MMQ for iq2_ks, iq2_k, iq2_k_r4

* Lookup is still beter for MMQ if we get 4 values at once

* Minor

---------

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

2025-07-08 19:44:48 +02:00

..

cmake

Merge mainline llama.cpp (#3)

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

include

Chnage KQ mask padding to 64 (#574)

2025-07-03 10:43:27 +02:00

src

Faster prompt processing for IQ2_KS, IQ2_K, IQ2_K_R4 (#593)

2025-07-08 19:44:48 +02:00

.gitignore

Merge mainline llama.cpp (#3)

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

CMakeLists.txt

Merge vulkan code from mainline up to commit of 6/28/2025 (#563)

2025-07-02 08:49:42 +02:00