ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-23 07:59:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

IQ1_M_R4: better 1.75 bpw quants (#187)

Browse Source 
* iq1_m_r4: basics (quantize/dequantize)

* iq1_m_r4: Zen4 gemm

* iq1_m_r4: neon gemm

* iq1_m_r4: switch to q8_0_x4 also on AVX2/Zen4

With the deltas being per group of 8, we cannot make use
of the q8 sums stored in q8_1, so we get a tiny gain by
using q8_0_x4.

* iq1_m_r4: rename mul_mat_iq1_m_r4_q8_1 to mul_mat_iq1_m_r4_q8_0

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2025-02-06 14:08:52 +02:00
committed by GitHub
parent 1b64fb3ed5
commit 7c94c3da56
11 changed files with 553 additions and 230 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
include/llama.h
View File

@@ -197,6 +197,7 @@ extern "C" {
LLAMA_FTYPE_MOSTLY_IQ3_S_R4 = 226, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ2_M_R4 = 229, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ4_XS_R4 = 230, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ1_M_R4 = 231, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q6_0_R4 = 335, // except 1d tensors
LLAMA_FTYPE_MOSTLY_BF16_R16 = 232, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ2_BN_R4 = 337, // except 1d tensors