llama_cpp_for_radxa_dragon_.../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
..
cmake
include ggml: add GATED_DELTA_NET op (#19504) 2026-03-07 15:41:10 +08:00
src metal : extend mul_mv_ext to BF16, Q2_K, Q3_K (#20250) 2026-03-09 16:48:12 +02:00
.gitignore
CMakeLists.txt