Merge commit '9230dbe2c7' into concedo_experimental

# Conflicts:
#	ggml/src/ggml-cpu/CMakeLists.txt
#	src/llama-graph.cpp
#	tools/server/README.md
This commit is contained in:
Concedo 2025-06-21 00:01:29 +08:00
commit c16d672ce4
29 changed files with 2666 additions and 2457 deletions

View file

@ -195,6 +195,9 @@ 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;