talk-llama : sync llama.cpp

ggml-ci
This commit is contained in:
Georgi Gerganov
2025-08-18 20:30:45 +03:00
parent 33c3c2fe2e
commit fc45bb8625
28 changed files with 1877 additions and 255 deletions
@@ -35,6 +35,7 @@ static std::string llama_model_ftype_name(llama_ftype ftype) {
case LLAMA_FTYPE_MOSTLY_Q5_0: return "Q5_0";
case LLAMA_FTYPE_MOSTLY_Q5_1: return "Q5_1";
case LLAMA_FTYPE_MOSTLY_Q8_0: return "Q8_0";
case LLAMA_FTYPE_MOSTLY_MXFP4_MOE: return "MXFP4 MoE";
case LLAMA_FTYPE_MOSTLY_Q2_K: return "Q2_K - Medium";
case LLAMA_FTYPE_MOSTLY_Q2_K_S: return "Q2_K - Small";
case LLAMA_FTYPE_MOSTLY_Q3_K_S: return "Q3_K - Small";