tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 03:55:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

common : improve -ctv -ctk CLI arguments (#10806)

Browse Source 
* common : improve ctv ctk cli argument

* regenerate docs

* even better approach

* use std::vector
This commit is contained in:
Xuan Son Nguyen
2024-12-12 22:53:05 +01:00
committed by GitHub
parent 274ec65af6
commit adffa6ffd5
5 changed files with 60 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
common/common.h
View File

@ -286,8 +286,8 @@ struct common_params {
bool warmup = true; // warmup run
bool check_tensors = false; // validate tensor data
std::string cache_type_k = "f16"; // KV cache data type for the K
std::string cache_type_v = "f16"; // KV cache data type for the V
ggml_type cache_type_k = GGML_TYPE_F16; // KV cache data type for the K
ggml_type cache_type_v = GGML_TYPE_F16; // KV cache data type for the V
// multimodal models (see examples/llava)
std::string mmproj = ""; // path to multimodal projector // NOLINT