cuda: AMD RDNA4 Q1_0/Q2_0 — HIP-path vec_dots (+37%/+16% decode), opt-in quant dedup, opt-in hipBLASLt prefill routes - #116

cuda: AMD RDNA4 Q1_0/Q2_0 — HIP-path vec_dots (+37%/+16% decode), opt-in quant dedup, opt-in hipBLASLt prefill routes#116

The-Monk wants to merge 58 commits into

PrismML-Eng:prismPrismML-Eng/llama.cpp:prismfrom

The-Monk:rdna4-q1q2The-Monk/prism-llama.cpp:rdna4-q1q2Copy head branch name to clipboard