]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
Expose generation timings from server & update completions.js (#2116)
authorTobias Lütke <redacted>
Wed, 5 Jul 2023 20:51:13 +0000 (16:51 -0400)
committerGitHub <redacted>
Wed, 5 Jul 2023 20:51:13 +0000 (16:51 -0400)
commit31cfbb1013a482e89c72146e2063ac4362becae7
treeb6479860979f90d185a132efe883ae7fb62b07f5
parent983b555e9ddb36703cee4d22642afe958de093b7
Expose generation timings from server & update completions.js (#2116)

* 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 <redacted>
examples/server/README.md
examples/server/completion.js.hpp
examples/server/deps.sh
examples/server/index.html.hpp
examples/server/public/completion.js
examples/server/public/index.html
examples/server/server.cpp
llama.cpp
llama.h