vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

build : enable more non-default compiler warnings (#3200)

Browse source
This commit is contained in:
Cebtenzzre 2023-09-28 17:41:44 -04:00 • committed by GitHub
parent 0ccfc62a96
commit bc39553c90
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
16 changed files with 285 additions and 267 deletions
Download patch file Download diff file Expand all files Collapse all files

1
examples/quantize/quantize.cpp
View file

@ -72,6 +72,7 @@ static bool try_parse_ftype(const std::string & ftype_str_in, llama_ftype & ftyp
// usage:
// ./quantize [--allow-requantize] [--leave-output-tensor] models/llama/ggml-model.gguf [models/llama/ggml-model-quant.gguf] type [nthreads]
//
[[noreturn]]
static void usage(const char * executable) {
printf("usage: %s [--help] [--allow-requantize] [--leave-output-tensor] model-f32.gguf [model-quant.gguf] type [nthreads]\n\n", executable);
printf(" --allow-requantize: Allows requantizing tensors that have already been quantized. Warning: This can severely reduce quality compared to quantizing from 16bit or 32bit\n");