Optimize AVX2 ggml_vec_dot_q4_0_q8_0: two FMA accumulator chains by codspeed-hq[bot] · Pull Request #31 · AvalancheHQ/llama.cpp

Performance Gate Passed

✅ 28 untouched benchmarks

_{Comparing codspeed-optim-unroll-the-avx2-ggml-vec-dot-q4-0-q8-0-loop-into-t-1785229421638 (fa9c3be) with master (46819c9)}