vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

server : smart slot selection using Longest Common Prefix (#7728)

Browse source 
* server : Smart selection of available slot using Longest Common Substring

* add usage

* remove trailing whitespaces

* Use Longest Common Prefix (LCP) instead of LCS

* Rename argument
This commit is contained in:
sasha0552 2024-06-08 07:50:31 +00:00 • committed by GitHub
parent da799b4189
commit 7a16ce7db2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 140 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

2
common/common.h
View file

@ -203,6 +203,8 @@ struct gpt_params {
std::string slot_save_path;
float slot_prompt_similarity = 0.5f;
// batched-bench params
bool is_pp_shared = false;