diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2025-03-21 07:24:22 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-03-21 07:24:22 +0100 |
| commit | ddc8eee10ee9216de57429167e6f74e618577d93 (patch) | |
| tree | 1dc5d251aa32e1bc6b1e3c4e68ea8619a89a5697 /include/llama.h | |
| parent | b8d1fac97b756968b86b470d44bb1026ded7157a (diff) | |
FlashMLA-3: the best of both worlds (CPU only) (#273)
* Repack a model with the quantize tool
* WIP
* Fixed various issues
As we don't have a way to tell if a repacked quant has been modified,
I had to remove the modification at the expense of a slight decrease
in performance. This affects q8_0_r8, q8_KV_r8, q8_k_r8 on Zen4, and
q4_0_r8 on ARM.
* Create wk_b and wv_b as Q8_0_R8 if the wkv_b type is interleaved
* Fix GCC 13.3 compilation error
* Another one
* Add missing include
* FlashMLA-3: the best of both worlds - CPU only
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'include/llama.h')
0 files changed, 0 insertions, 0 deletions