MCPcopy Create free account
hub / github.com/appdevforall/CodeOnTheGo / ggml_quantize_free

Function ggml_quantize_free

subprojects/llama.cpp/ggml/src/ggml.c:7515–7527  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

7513}
7514
7515void ggml_quantize_free(void) {
7516 ggml_critical_section_start();
7517
7518 iq2xs_free_impl(GGML_TYPE_IQ2_XXS);
7519 iq2xs_free_impl(GGML_TYPE_IQ2_XS);
7520 iq2xs_free_impl(GGML_TYPE_IQ2_S);
7521 iq2xs_free_impl(GGML_TYPE_IQ1_S);
7522 iq2xs_free_impl(GGML_TYPE_IQ1_M);
7523 iq3xs_free_impl(256);
7524 iq3xs_free_impl(512);
7525
7526 ggml_critical_section_end();
7527}
7528
7529bool ggml_quantize_requires_imatrix(enum ggml_type type) {
7530 return

Callers 2

llama_backend_freeFunction · 0.85
mainFunction · 0.85

Calls 4

iq2xs_free_implFunction · 0.85
iq3xs_free_implFunction · 0.85

Tested by 1

mainFunction · 0.68