CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-02 09:12:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : add server parameters for draft model cache type (#13782)

Browse Source 
Co-authored-by: aa956 <27946957+aa956@users.noreply.github.com>
This commit is contained in:
aa956
2025-06-19 16:01:03 +03:00
committed by GitHub
parent 456af35eb7
commit d67341dc18
4 changed files with 33 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
common/common.h
View File

@@ -199,6 +199,9 @@ struct common_params_speculative {
float p_split = 0.1f; // speculative decoding split probability
float p_min = 0.75f; // minimum speculative decoding probability (greedy)
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
struct cpu_params cpuparams;
struct cpu_params cpuparams_batch;