Skip to content

Distribute and run LLMs with a single file.

Commits on main

Add gpu accel probe (#953)
Davide Eynard committed 6 months ago
0843312
New release version: update version.h and docs (#952)
Davide Eynard committed 6 months ago
6490e16
Docs Updates (#949)
angpt committed 6 months ago
e487db2
Win build improvements (#940)
Davide Eynard committed 7 months ago
f643524
Update llama.cpp submodule to 5e9c63546 (#941)
Davide Eynard committed 7 months ago
ea67fea
b355cee
Add windows build scripts for CUDA (#924)
Davide Eynard committed 7 months ago
8a629f4
Fix block-size assumption (#935)
Davide Eynard committed 7 months ago
e7e6796
c0c19fd
e08323f
Add tinyblasStrsmBatched kernel (#923)
Davide Eynard committed 7 months ago
eb7f66c
Add support for vulkan dylibs (#892)
Davide Eynard committed 7 months ago
c7d7e3e
Fix README_0.10.0 (#918)
Davide Eynard committed 8 months ago
b02f2e0
llamafile reloaded (v0.10.0) (#867)
Davide Eynard committed 8 months ago
4cc1a5f
update supported OpenBSD versions (#897)
Stuart Henderson committed 8 months ago
7e7d33c
Fixed broken llamafile URL in docs (#873)
Davide Eynard committed 9 months ago
ed9016c
fix(update-llama-cpp): Use `new_build_wip` as base ref. (#850)
David de la Iglesia Castro committed 10 months ago
520847f
chore: Add `update-llama-cpp` workflow. (#846)
David de la Iglesia Castro committed 10 months ago
3ff983f
feat: move docs to mkdocs (#824)
Nathan Brake committed 1 year ago
9509d91
chore: llama.cpp as submodule (#819)
Nathan Brake committed 1 year ago
9d975d0
chore: convert stable diffusion to submodule (#818)
Nathan Brake committed 1 year ago
7ee25fe
chore: integrate whisper.cpp as a submodule (#813)
Nathan Brake committed 1 year ago
1a5d1c2
accept array in chat message content field
henfiber committed 1 year ago
1562542
Release llamafile v0.9.3
CJ Pais committed 1 year ago
ff0c02e
51b357b
use code from ik
CJ Pais committed 1 year ago
e7b29e1