ggml: added cleanups in ggml_quantize_free (llama/19278)

Add missing cleanup calls for IQ2_S, IQ1_M quantization types and IQ3XS with 512 blocks during quantization cleanup.

diff --git a/src/ggml.c b/src/ggml.c
index e1471b540ed1c5b54e670f371f48e87ccfe1c6ad..500cb6b72f927904e30fa407618dcf2e29e17268 100644 (file)
--- a/src/ggml.c
+++ b/src/ggml.c
@@ -7517,8 +7517,11 @@ void ggml_quantize_free(void) {
 
     iq2xs_free_impl(GGML_TYPE_IQ2_XXS);
     iq2xs_free_impl(GGML_TYPE_IQ2_XS);
+    iq2xs_free_impl(GGML_TYPE_IQ2_S);
     iq2xs_free_impl(GGML_TYPE_IQ1_S);
+    iq2xs_free_impl(GGML_TYPE_IQ1_M);
     iq3xs_free_impl(256);
+    iq3xs_free_impl(512);
 
     ggml_critical_section_end();
 }