diff options
| author | Kerfuffle <44031344+KerfuffleV2@users.noreply.github.com> | 2023-06-13 04:23:23 -0600 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-06-13 04:23:23 -0600 |
| commit | 74d4cfa3438cb58bd177eed30014e6588694aaa8 (patch) | |
| tree | 8252d459812376411bcf8508ad7d1f059670601a /llama.h | |
| parent | 74a6d922f12ccfe16b0c265f43be8978c6f25e98 (diff) | |
Allow "quantizing" to f16 and f32 (#1787)
* Allow "quantizing" to f16 and f32
Fix an issue where quantizing didn't respect LLAMA_NO_K_QUANTS
Add brief help to the list of quantization types in the quantize tool
Ignore case for quantization type arguments in the quantize tool
Diffstat (limited to 'llama.h')
0 files changed, 0 insertions, 0 deletions