ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-01-26 17:20:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

Q6_0_R4 (#122)

Browse Source 
* Adding q6_0_r4

We get PP-512(LLaMA-3.1-8B) = 257 t/s on a Ryzen-7950X.

* q6_0_r4: NEON

We get PP-512(LLaMA-3.1-8B) = 95 t/s on M2-Max.
In terms of ops, q6_0_r4 is identical to q5_0_r4
except for loading the high bits being
vld1q_u8_x2 instead of vld1q_u8. It is strange that
this can make a 5% difference in performance, especially
considering that this is amortized (re-used) over 8 columns
in the right matrix. Or am I running out of vector registers?

* Fix AVX2

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2024-12-03 14:48:26 +01:00
committed by GitHub
parent d9593f3689
commit bb699e1e6b
8 changed files with 334 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/quantize/quantize.cpp
View File

@@ -43,6 +43,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
{ "IQ4_NL_X4",LLAMA_FTYPE_MOSTLY_IQ4_NL_X4," 4.50 bpw non-linear quantization", },
{ "Q4_0_R4", LLAMA_FTYPE_MOSTLY_Q4_0_R4, " 4.50 bpw quantization", },
{ "Q5_0_R4", LLAMA_FTYPE_MOSTLY_Q5_0_R4, " 5.50 bpw quantization", },
{ "Q6_0_R4", LLAMA_FTYPE_MOSTLY_Q6_0_R4, " 6.50 bpw quantization", },
{ "Q8_0_R4", LLAMA_FTYPE_MOSTLY_Q8_0_R4, " 8.50 bpw quantization", },
{ "IQ4_XS", LLAMA_FTYPE_MOSTLY_IQ4_XS, " 4.25 bpw non-linear quantization", },
{ "IQ4_KS", LLAMA_FTYPE_MOSTLY_IQ4_KS, " 4.25 bpw non-linear quantization", },