mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2025-04-16 11:36:08 +00:00

* vulkan: initial support for IQ1_S and IQ1_M quantizations * vulkan: define MMV kernels for IQ1 quantizations * devops: increase timeout of Vulkan tests again * vulkan: simplify ifdef for init_iq_shmem