mirrors/cosmopolitan
1
0
Fork 0
mirror of https://github.com/jart/cosmopolitan.git synced 2025-09-10 10:43:48 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Import llama.cpp

Browse source 
https://github.com/ggerganov/llama.cpp
0b2da20538d01926b77ea237dd1c930c4d20b686
See third_party/ggml/README.cosmo for changes
This commit is contained in:
Justine Tunney 2023-04-27 14:31:20 -07:00
parent f42089d5c6
commit e8b43903b2
No known key found for this signature in database
GPG key ID: BE714B4575D6E328
14 changed files with 18313 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

21
third_party/ggml/README.cosmo vendored Normal file
View file

@ -0,0 +1,21 @@
DESCRIPTION
ggml is a machine learning library useful for LLM inference on CPUs
LICENSE
MIT
ORIGIN
https://github.com/ggerganov/llama.cpp
commit 0b2da20538d01926b77ea237dd1c930c4d20b686
Author: Stephan Walter <stephan@walter.name>
Date: Wed Apr 26 20:26:42 2023 +0000
ggml : slightly faster AVX2 implementation for Q5 (#1197)
LOCAL CHANGES
- Refactor headers per cosmo convention
- Replace code like 'ggjt' with READ32BE("ggjt")
- Remove C++ exceptions; use Die() function instead