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

Function ggml_is_quantized

subprojects/llama.cpp/ggml/src/ggml.c:1288–1290  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

1286}
1287
1288bool ggml_is_quantized(enum ggml_type type) {
1289 return type_traits[type].is_quantized;
1290}
1291
1292const char * ggml_op_name(enum ggml_op op) {
1293 return GGML_OP_NAME[op];

Callers 15

merge_tensorMethod · 0.85
llama_contextMethod · 0.85
llama_init_from_modelFunction · 0.85
build_rope_shiftMethod · 0.85
init_tensor_uniformFunction · 0.85
tensor_to_floatFunction · 0.85
build_graphMethod · 0.85
common_debug_cb_evalFunction · 0.85
ggml_add_cast_implFunction · 0.85
fa_rows_colsFunction · 0.85

Calls

no outgoing calls

Tested by 3

init_tensor_uniformFunction · 0.68
tensor_to_floatFunction · 0.68
build_graphMethod · 0.68