Files
llama.cpp/ggml
Paul Flynn e22cd0aa15 metal : extend mul_mv_ext to BF16, Q2_K, Q3_K (#20250)
Enable mul_mv_ext small-batch kernels (BS 2-8) for BF16, Q2_K,
and Q3_K quantization types. These types previously fell through
to the slower single-row mul_mv path.

BF16 uses the float4 dequantize path (like F16). Q2_K and Q3_K
use the float4x4 K-quant path (like Q4_K/Q5_K/Q6_K).

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-09 16:48:12 +02:00
..
2024-07-13 18:12:39 +02:00