ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-29 10:51:51 +00:00
Code Issues Packages Projects Releases Wiki Activity

Adding Q6_0 (#77)

Browse Source 
* Adding q6_0 - basics + AVX2/Zen4 working

* Adding q6_0: CUDA dequantize works, but not mmvq

* Adding q6_0: CUDA mmvq works

* Adding q6_0: CUDA cpy, so Q6_0 can be used for KV-cache

* Add q6_0 to CPU flash attention

Disappointing result: for LlaMA-3.2-1B, q6_0 K- and V-cache
gives about the same PPL as q8_0 K-cache and q4_0 V-cache,
while needing the exact same RAM.
I.e., what was the point?

* q6_0: slightly better kv-cache result

Better than q8_0+q4_0, but not as good as q8_0+iq4_nl

* q6_0: works on ARM_NEON

* q6_0: dequantize works on Metal, but not vector dot product

* q6_0: it now works on Metal

Outperforms q5_0 by a significant margin. E.g.
| model                          |       size |     params | backend    | ngl | threads |          test |              t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | ------: | ------------: | ---------------: |
| llama 8B Q6_0                  |   6.08 GiB |     8.03 B | Metal      | 100 |       4 |         tg128 |     44.02 ± 0.08 |
| llama 8B Q5_0                  |   5.21 GiB |     8.03 B | Metal      | 100 |       4 |         tg128 |     40.13 ± 0.12 |
| llama 8B Q6_0                  |   6.08 GiB |     8.03 B | Metal      | 100 |       4 |         pp512 |    500.55 ± 0.32 |
| llama 8B Q5_0                  |   5.21 GiB |     8.03 B | Metal      | 100 |       4 |         pp512 |    448.02 ± 0.27 |

* q6_0: can now be used for kv-cache on Metal

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2024-10-02 15:22:13 +03:00
committed by GitHub
parent d6909ed6f0
commit cce49832c1
19 changed files with 678 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/include/ggml.h
View File

@@ -392,6 +392,7 @@ extern "C" {
GGML_TYPE_Q4_0_4_8 = 32,
GGML_TYPE_Q4_0_8_8 = 33,
//
GGML_TYPE_Q6_0 = 133,
GGML_TYPE_IQ1_BN = 134,
GGML_TYPE_IQ2_BN = 135,
GGML_TYPE_Q8_K64 = 136,
@@ -447,6 +448,7 @@ extern "C" {
GGML_FTYPE_MOSTLY_Q4_0_4_8 = 26, // except 1d tensors
GGML_FTYPE_MOSTLY_Q4_0_8_8 = 27, // except 1d tensors
//
GGML_FTYPE_MOSTLY_Q6_0 = 127, // except 1d tensors
GGML_FTYPE_MOSTLY_IQ1_BN = 128, // except 1d tensors
GGML_FTYPE_MOSTLY_IQ2_BN = 129, // except 1d tensors
GGML_FTYPE_MOSTLY_IQ2_K = 130, // except 1d tensors