llama.cpp releases
· Infrastructure
b10165
vulkan: add iq4_nl support back to FA (#24585) vulkan: add iq4_nl support back to FA I was originally concerned about wasting shared memory on the LUT, but it's small and unlikely to matter in practice. Also support q1_0 for non-coopmat2. Fixes #23681 remove q1_0 FA support Website: https://llama.app macOS/iOS: macOS A