mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-04-26 01:19:20 +00:00
@@ -359,6 +359,7 @@ struct gpt_params {
|
||||
bool split_mode_graph_scheduling = false; // if true, force split mode graph scheduling
|
||||
//bool split_mode_f16 = true; // if true, intermediate results will be cast to f16 before copying to other GPUs to perform reduce ops
|
||||
bool scheduler_async = false; // if true, in split mode graph the scheduler will use multiple threads to evaluate the graph
|
||||
int fused_delta_net = 65536; // use fused delta-net if number of tokens in the batch is less than this value
|
||||
bool has_mtp = false; // enable MTP if supported by the model
|
||||
|
||||
std::string cache_type_k = "f16"; // KV cache data type for the K
|
||||
|
||||
Reference in New Issue
Block a user