Skip to content

Distribute and run LLMs with a single file.

Commits on main

Update GGML_HIP_UMA (#473)
Djip007 committed 2 years ago
a28250b
Add back missing build rule
Justine Tunney committed 2 years ago
842a421
Fix the build
Justine Tunney committed 2 years ago
1c08fad
Introduce new llamafile server
Justine Tunney committed 2 years ago
e0656ea
Make the build go a little faster
Justine Tunney committed 2 years ago
8b9be96
Add double-conversion
Justine Tunney committed 2 years ago
581a173
Improve CPU brand detection
Justine Tunney committed 2 years ago
e973fa2
Add stable-diffusion.cpp
Justine Tunney committed 2 years ago
3b7b1e3
Add Mozilla logo to README
Stephen Hood committed 2 years ago
8e23c73
add Mozilla logo
Stephen Hood committed 2 years ago
5447f2d
9cd8d70
Upgrade to Cosmopolitan v3.3.10 (#460)
jeromew committed 2 years ago
7d8dd1b
github: add ci (#454)
Brian committed 2 years ago
31419d0
397175e
github: add issue templates (#442)
Brian committed 2 years ago
076dfb0
Release llamafile v0.8.6
Justine Tunney committed 2 years ago
81cfbcf
Upgrade to Cosmopolitan v3.3.8
Justine Tunney committed 2 years ago
866a129
Don't print special tokens for now
Justine Tunney committed 2 years ago
69c2dd3
Disable GPU in llava-quantize
Justine Tunney committed 2 years ago
ea2a96e
Release llamafile v0.8.5
Justine Tunney committed 2 years ago
b79ecf4
Recompute llamafile-quantize documentation
Justine Tunney committed 2 years ago
07e87bf
Upgrade to Cosmopolitan v3.3.7
Justine Tunney committed 2 years ago
261dfe7
Add missing CPUID check
Justine Tunney committed 2 years ago
e75caa1
Make some more benchmark tool fixes
Justine Tunney committed 2 years ago
e675719
Reclaim mapped memory
Justine Tunney committed 2 years ago
4451c6d