extern/whisper.cpp
1
0
Fork 1
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-08-09 08:36:02 +02:00
Code Issues Packages Projects Releases Wiki Activity

talk-llama : sync llama.cpp

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-05-13 13:20:19 +03:00
parent a14c89aefa
commit f890560575
25 changed files with 2847 additions and 1125 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/talk-llama/llama-quant.cpp
View File

@ -519,7 +519,7 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::
nthread = std::thread::hardware_concurrency();
}
// mmap consistently increases speed Linux, and also increases speed on Windows with
// mmap consistently increases speed on Linux, and also increases speed on Windows with
// hot cache. It may cause a slowdown on macOS, possibly related to free memory.
#if defined(__linux__) || defined(_WIN32)
constexpr bool use_mmap = true;
@ -529,7 +529,7 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::
llama_model_kv_override * kv_overrides = nullptr;
if (params->kv_overrides) {
auto v = (std::vector<llama_model_kv_override>*)params->kv_overrides;
auto * v = (std::vector<llama_model_kv_override>*)params->kv_overrides;
kv_overrides = v->data();
}