diff options
| author | Kawrakow <48489457+ikawrakow@users.noreply.github.com> | 2023-08-27 15:19:59 +0300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-08-27 15:19:59 +0300 |
| commit | a6d1189fdd4c1ab4ba23f9d777f8950901dcffb2 (patch) | |
| tree | d9a96c3adbf57aad406bfb5bd304765615933060 /examples/perplexity/perplexity.cpp | |
| parent | c48c5bb0b06385f6c708339188d2aaf2bc278477 (diff) | |
k_quants tuning for Falcon-7b (#2816)
* Make ggml-cuda.cu build with QK_K = 64
Using LLAMA_CUDA_FORCE_DMMV = ON and -nommq it runs and produces
a meaningful result.
* k_quants tuning for Falcon-7b
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'examples/perplexity/perplexity.cpp')
0 files changed, 0 insertions, 0 deletions