Skip to content

Distribute and run LLMs with a single file.

Commits on main

Add CI (#126)
Vinicius Woloszyn committed 2 years ago
dadd5a7
Update README to clarify Darwin kernel versioning
Justine Tunney committed 2 years ago
a56ffd4
Set logger callback for Apple Metal
Justine Tunney committed 2 years ago
3d81e22
Make it easier to override CPPFLAGS
Justine Tunney committed 2 years ago
9579b73
Add WSL CUDA to GPU section (#105)
Chandler committed 2 years ago
658b18a
Fix README changing SSE3 to SSSE3
Justine Tunney committed 2 years ago
47d8a8f
Fix README examples for certain UNIX shells
Justine Tunney committed 2 years ago
4da8e2e
Change README to list Mixtral Q5 (instead of Q3)
Justine Tunney committed 2 years ago
faa7430
Fix CLI README examples
Justine Tunney committed 2 years ago
6b0b64f
Add Mixtral 8x7B Q3_K_M to README.md
Justine Tunney committed 2 years ago
6348000
Release llamafile v0.4
Justine Tunney committed 2 years ago
188f7fc
Tune CUDA build scripts some more
Justine Tunney committed 2 years ago
2f41a6d
Have tinyBLAS conform to project style
Justine Tunney committed 2 years ago
875c8a6
Write log to /dev/null when main.log fails to open
Justine Tunney committed 2 years ago
fcc727a
Make tinyBLAS go 95% as fast as cuBLAS (#97)
Gautham committed 2 years ago
a7de00b
Improve GEMM performance by nearly 2x (#93)
Jōshin committed 2 years ago
9d85a72
Fix irrelevant bounds check in cuda.c (#95)
Jōshin committed 2 years ago
99f1e92
Fix error with Apple Metal GPU compile
Justine Tunney committed 2 years ago
1d8617f
Make GGML DLL easier to bundle
Justine Tunney committed 2 years ago
536125c
Add missing GGML function to CUDA module
Justine Tunney committed 2 years ago
09fdeb3
Fix CUDA build on Windows
Justine Tunney committed 2 years ago
72b812a
Add SD ops, kernels
Georgi Gerganov committed 2 years ago
782c81c
Update the llamafile manual
Justine Tunney committed 2 years ago
69ec1e4
Remove unintended exit() in cuda.c
Justine Tunney committed 2 years ago
6bc1b0f
Polyfill $HOME on some Windows systems
Justine Tunney committed 2 years ago
93178c9
Fix tinyBLAS support
Justine Tunney committed 2 years ago
dfd3804
Synchronize with llama.cpp upstream
Justine Tunney committed 2 years ago
820d42d
Improve markdown and syntax highlighting in server (#88)
Dominic Szablewski committed 2 years ago
c236a71
Make it possible for CUDA to extract prebuilt DSOs
Justine Tunney committed 2 years ago
2849b08