Files
llama.cpp/ggml
Millaguie 4d9a6f55b6 ggml: add block_dt3, the dual-plane ternary block
DT3 stores w_i = d[0]*t0_i + d[1]*t1_i with t in {-1,0,+1}, two ternary
planes over a 128-element block: 56 bytes, 3.5 bpw exactly.

Each plane uses the tq1_0 base-3 packing with every constant halved for
the smaller block (qs 48->24 B, qh 4->2 B, qs passes over 16 then 8
bytes instead of 32 then 16), which tiles 128 with no leftover bytes.
Reducing tq1_0 to 128 without halving the passes does not tile: with a
24-byte qs the first pass covers nothing and the second overruns.
2026-08-10 12:58:49 +02:00
..
2024-07-13 18:12:39 +02:00