Skip to content

Distribute and run LLMs with a single file.

Commits on main

f6ee33c
c2bc6e6
Make edits to new OpenAI API README section
Justine Tunney committed 2 years ago
e0127f7
Add OpenAI API tutorial to README (#159)
Brian committed 2 years ago
8492db2
Apply 2D blocking to all kernels (#156)
Gautham committed 2 years ago
c0589f0
Update README.md
Justine Tunney committed 2 years ago
d802427
Fix llamafile.h regression
Justine Tunney committed 2 years ago
5fcffd1
Add --cli flag and show unified man page on --help
Justine Tunney committed 2 years ago
5cf6e76
Add llamafile-convert command (#112)
Chandler committed 2 years ago
1dcf274
Add 2D blocking to tinyBLAS GemmEx (#153)
Gautham committed 2 years ago
1d9fa85
Don't schlep weights into CPU when using GPU
Justine Tunney committed 2 years ago
f0e86e1
Fix repeat_last_n in OpenAI server
Justine Tunney committed 2 years ago
f1410a1
Add Phi-2 architecture support
Justine Tunney committed 2 years ago
6423228
Fix build ordering issue
Justine Tunney committed 2 years ago
8f73d39
Increase server max payload size
Justine Tunney committed 2 years ago
3119f09
Fix indentation nit
Justine Tunney committed 2 years ago
3b9d3f3
Unify llamafile-server command into llamafile
Justine Tunney committed 2 years ago
b86dcb7
Favor `-c 0` over `-c 6700` in README.md
Justine Tunney committed 2 years ago
b072b35
Fix sed commands in README.md
Justine Tunney committed 2 years ago
2b91eff
Release llamafile v0.4.1
Justine Tunney committed 2 years ago
f6ea6bf
Improve llamafile manual
Justine Tunney committed 2 years ago
5c7ff6e
Fix SIGILL on older Intel/AMD CPUs w/o F16C
Justine Tunney committed 2 years ago
3490afa
Remove GPU warnings from option parser
Justine Tunney committed 2 years ago
0164146
Revert "Support ROCm at compile-time (#122)"
Justine Tunney committed 2 years ago
18c2821
Improve README examples
Justine Tunney committed 2 years ago
9e972b2
Fix regression with --grammar flag
Justine Tunney committed 2 years ago
0984ed8
Support bos token in llava-cli
Justine Tunney committed 2 years ago
9de5686
Fix OpenAI server sampling w.r.t. temp and seed
Justine Tunney committed 2 years ago
9e4bf29
Support ROCm at compile-time (#122)
Aaryaman Vasishta committed 2 years ago
8bea4e1
586b408