feat: first draft of q2_k quantization support

2025-11-03 18:24:41 +08:00
parent 25e5dd4645
commit 9e1a4f2942
8 changed files with 972 additions and 1 deletions
@@ -2120,7 +2120,7 @@ gpt_params_context gpt_params_parser_init(gpt_params & params, llama_example ex,
    ));
    add_opt(llama_arg(
        {"--comm-datatype"}, "TYPE",
-        format("Datatype for communication, currently support f32, q8_0, q4_0 or f32_sparsity (default: %s)", params.comm_datatype.c_str()),
+        format("Datatype for communication, currently support f32, q8_0, q4_0, q2_k or f32_sparsity (default: %s)", params.comm_datatype.c_str()),
        [](gpt_params & params, const std::string & value) {
            params.comm_datatype = value;
        }