IQ4_NL_X4 (#118)

* Adding iq4_nl_x4

Looks very promising - I get PP-512(LLaMA-3.1-8B) = 230 t/s
on the Ryzen-7950X! This is faster than any other quant and
~40% faster than iq4_nl.

* iq4_nl_x4: getting amazing

This Zen4 variant gets us to PP-512(LLaMA-3.1-8B) = 263 t/s!

* iq4_nl_x4: AVX2

Here we gain only 25% compared to iq4_nl

* iq4_nl_x4: NEON

On M2-Max we get PP-512(LLaMA-3.1-8B) = 109.7 t/s, up from
82.4 t/s for iq4_nl.

* iq4_nl_x4: minor NEON improvement and cleanup

This gets us to 110.3 t/s. In comparison,
IQ4_NL_4_4 in mainline llama.cpp achieves 92.3 t/s.

* iq4_nl_x4: NEON specialization for matrix x vector

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>

1 files changed, 5 insertions, 0 deletions

diff --git a/ggml/src/ggml-common.h b/ggml/src/ggml-common.h
index f0c1ae68..2af3323d 100644
--- a/ggml/src/ggml-common.h
+++ b/ggml/src/ggml-common.h
@@ -419,6 +419,11 @@ typedef struct {
     uint8_t qs[QK4_NL/2];
 } block_iq4_nl;
 static_assert(sizeof(block_iq4_nl) == sizeof(ggml_half) + QK4_NL/2, "wrong iq4_nl block size/padding");
+typedef struct {
+    ggml_half d[4];
+    uint8_t qs[2*QK4_NL];
+} block_iq4_nl_x4;
+static_assert(sizeof(block_iq4_nl_x4) == 4*sizeof(ggml_half) + 2*QK4_NL, "wrong iq4_nl_x4 block size/padding");
 
 typedef struct {
     ggml_half d;