ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-24 16:39:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add command line arg to disable rope cache

Browse Source
This commit is contained in:
Iwan Kawrakow
2025-11-03 08:20:03 +02:00
parent aa76ff2c9d
commit 525dda2e80
8 changed files with 77 additions and 95 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
common/common.h
View File

@@ -112,7 +112,7 @@ enum common_reasoning_format {
enum common_webui {
COMMON_WEBUI_NONE,
COMMON_WEBUI_AUTO,
COMMON_WEBUI_LLAMACPP,
COMMON_WEBUI_LLAMACPP,
};
common_webui common_webui_from_name(const std::string& format);
@@ -249,6 +249,7 @@ struct gpt_params {
bool fused_up_gate = true; // fused up*unary(gate) op
bool fused_mmad = true; // fused mul+multi_add op
bool grouped_expert_routing = false; // if to use grouped expert routing (BailingMoeV2 arch)
bool rope_cache = true; // if to use RoPE cache (for supported models)
int min_experts = -1;
float thresh_experts = 0;