diff options
| author | Stephan Walter <stephan@walter.name> | 2023-03-28 15:56:03 +0000 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-03-28 18:56:03 +0300 |
| commit | c1f885067c61191a07a1aedf684168dda62f3f71 (patch) | |
| tree | 2bcb3f068942e2f16a92d70fec4bd623ac17ce28 /examples/quantize | |
| parent | e0670260fb50a882b37074112b1881fb0820cf77 (diff) | |
ggml : introduce structs for the q4 data blocks (#356)
* Introduce structs for the q4 data blocks
* ggml : rename quant struct variables + fix ARM_NEON
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Diffstat (limited to 'examples/quantize')
| -rw-r--r-- | examples/quantize/quantize.cpp | 4 |
1 files changed, 1 insertions, 3 deletions
diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp index f0230f5..3888ff5 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -4,8 +4,6 @@ #include <cstdio> #include <string> -const int QK = 32; - // usage: // ./llama-quantize models/llama/ggml-model.bin models/llama/ggml-model-quant.bin type // @@ -39,7 +37,7 @@ int main(int argc, char ** argv) { { const int64_t t_start_us = ggml_time_us(); - if (llama_model_quantize(fname_inp.c_str(), fname_out.c_str(), itype, QK)) { + if (llama_model_quantize(fname_inp.c_str(), fname_out.c_str(), itype)) { fprintf(stderr, "%s: failed to quantize model from '%s'\n", __func__, fname_inp.c_str()); return 1; } |