diff options
| author | Sebastián A <sebastian.aedo29@gmail.com> | 2023-03-12 17:15:00 -0300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-03-12 22:15:00 +0200 |
| commit | eb062bb012c4e131818dd757a6d3a757fdee3961 (patch) | |
| tree | 9c7865b0f4e8457252ce6b0b936496cc48d08723 /quantize.cpp | |
| parent | 7027a97837c351e0a7bc48db2027af368de382db (diff) | |
Windows fixes (#31)
* Apply fixes suggested to build on windows
Issue: https://github.com/ggerganov/llama.cpp/issues/22
* Remove unsupported VLAs
* MSVC: Remove features that are only available on MSVC C++20.
* Fix zero initialization of the other fields.
* Change the use of vector for stack allocations.
Diffstat (limited to 'quantize.cpp')
| -rw-r--r-- | quantize.cpp | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/quantize.cpp b/quantize.cpp index 0ae53733..14c7b277 100644 --- a/quantize.cpp +++ b/quantize.cpp @@ -289,6 +289,7 @@ bool llama_model_quantize(const std::string & fname_inp, const std::string & fna // ./llama-quantize models/llama/ggml-model.bin models/llama/ggml-model-quant.bin type // int main(int argc, char ** argv) { + ggml_time_init(); if (argc != 4) { fprintf(stderr, "usage: %s model-f32.bin model-quant.bin type\n", argv[0]); fprintf(stderr, " type = 2 - q4_0\n"); |