mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-09-15 18:13:29 +02:00
WakeUpMortyandGitHub
df750f76bb
* vulkan: add dedicated iq4_xs mat-vec shader Dedicated mul_mat_vec_iq4_xs for the dmmv path, replacing the generic fallback. ~+6-17% token generation on RDNA4 depending on model. Assisted-by: Pi agent with Qwen3.8 27B * vulkan iq4_xs: remove dead n_it unroll branch Remove the n_it <= 8 experimental branch that attempted to fully unroll the block loop. Since n_it is a runtime value, [[unroll]] is ignored by the compiler, making both branches equivalent. Kept the simple loop matching mul_mat_vec_iq3_s.comp.