diff options
author | Stephan Walter <stephan@walter.name> | 2023-07-05 16:13:06 +0000 |
---|---|---|
committer | GitHub <noreply@github.com> | 2023-07-05 19:13:06 +0300 |
commit | 1b107b8550dced48dc5f41184640061354226b96 (patch) | |
tree | a09a4c33c865828cd753c19af71c580f98735be5 /examples/server/index.html.hpp | |
parent | 8567c76b5326e862be0755a8dc1dd988223fcae3 (diff) |
ggml : generalize `quantize_fns` for simpler FP16 handling (#1237)
* Generalize quantize_fns for simpler FP16 handling
* Remove call to ggml_cuda_mul_mat_get_wsize
* ci : disable FMA for mac os actions
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Diffstat (limited to 'examples/server/index.html.hpp')
0 files changed, 0 insertions, 0 deletions