tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-02 05:15:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

Expose generation timings from server & update completions.js (#2116)

Browse Source 
* use javascript generators as much cleaner API

Also add ways to access completion as promise and EventSource

* export llama_timings as struct and expose them in server

* update readme, update baked includes

* llama : uniform variable names + struct init

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Tobias Lütke
2023-07-05 16:51:13 -04:00
committed by GitHub
parent 983b555e9d
commit 31cfbb1013
9 changed files with 1921 additions and 1363 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/server/deps.sh
View File

@ -4,10 +4,6 @@
# get the directory of this script file
DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
PUBLIC=$DIR/public
OUTPUT=$DIR/templats.hpp
echo "// Generated file, do not edit" > $OUTPUT
echo "" > $OUTPUT
echo "download js bundle files"
curl https://npm.reversehttp.com/@preact/signals-core,@preact/signals,htm/preact,preact,preact/hooks > $PUBLIC/index.js