diff options
author | Georgi Gerganov <ggerganov@gmail.com> | 2023-04-22 10:55:35 +0300 |
---|---|---|
committer | GitHub <noreply@github.com> | 2023-04-22 10:55:35 +0300 |
commit | 955ef9a5d53d8f911fe00580ac9bd0caa56430af (patch) | |
tree | d60f9ac6b426c8f3e59992691d7686c2d7ff89db /examples/chat-13B.bat | |
parent | c5aa5e577741d0359ad26ec50b9e21a74c65d911 (diff) |
ggml : alternative Q4_3 implementation using modified Q8_0 (#1109)
* ggml : prefer vzip to vuzp
This way we always use the same type of instruction across all quantizations
* ggml : alternative Q4_3 implementation using modified Q8_0
* ggml : fix Q4_3 scalar imlpementation
* ggml : slight improvement of Q4_3 - no need for loop unrolling
* ggml : fix AVX paths for Q8_0 quantization
Diffstat (limited to 'examples/chat-13B.bat')
0 files changed, 0 insertions, 0 deletions