llama.cpp/ggml
Rémy O 438a83926a
vulkan: add specific MMV kernels for IQ2 and IQ3 quants + optimizations (#11595)
* vulkan: implement specialized MMV kernels for IQ2 quantizations

* vulkan: add MMV kernels for IQ3 quants

* vulkan: Increase MMV batch size and unroll IQ LUT setup

* vulkan: fix init_iq_shmem for WG sizes larger than tables

* vulkan: common batch size for all I-quants
2025-02-28 09:42:52 +01:00
..
cmake cmake: Fix ggml backend dependencies and installation (#11818) 2025-02-27 09:42:48 +02:00
include ggml-cpu: Support s390x SIMD Instruction Set (#12019) 2025-02-22 21:39:24 +00:00
src vulkan: add specific MMV kernels for IQ2 and IQ3 quants + optimizations (#11595) 2025-02-28 09:42:52 +01:00
.gitignore vulkan : cmake integration (#8119) 2024-07-13 18:12:39 +02:00
CMakeLists.txt cmake: Fix ggml backend dependencies and installation (#11818) 2025-02-27 09:42:48 +02:00