This repository has been archived by the owner on Sep 12, 2024. It is now read-only.

implement new sampling logic for llama.cpp #36

Closed

hlhr202 opened this issue May 1, 2023 · 0 comments · Fixed by #38

Assignees

Labels

Member

hlhr202 commented May 1, 2023

llama.cpp introduce new sampling logic here:
ggerganov/llama.cpp#1126

hlhr202 self-assigned this

hlhr202 added the enhancement label

hlhr202 mentioned this issue

[ASK] enable cuda with manual compilation #34

Open

hlhr202 linked a pull request

that will close this issue

feature: llama cpp new sampling #38

Merged

hlhr202 closed this as completed in #38

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.