Skip to content

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Commits on main

stdin.fd
Michael Yang committed 2 years ago
f38353d
nolintlint
Michael Yang committed 2 years ago
201d853
lint
Michael Yang committed 2 years ago
e40145a
some gocritic
Michael Yang committed 2 years ago
c895a7d
nosprintfhostport
Michael Yang committed 2 years ago
dad7a98
nolintlint
Michael Yang committed 2 years ago
8ffb517
gofmt
Michael Yang committed 2 years ago
55f6eba
replace x/exp/slices with slices
Michael Yang committed 2 years ago
04f3c12
update welcome prompt in windows to `llama3` (#4779)
Jeffrey Morgan committed 2 years ago
d4a8610
Limit GPU lib search for now (#4777)
Jeffrey Morgan committed 2 years ago
476fb8e
revert tokenize ffi (#4761)
Michael Yang committed 2 years ago
829ff87
added tests for IsValidNamespace
Josh Yan committed 2 years ago
2e4da8e
use `int32_t` for call to tokenize (#4738)
Jeffrey Morgan committed 2 years ago
763bb65
speed up tests by only building static lib (#4740)
Jeffrey Morgan committed 2 years ago
7ca9605
eb2c443
278e25e
only generate on relevant changes
Michael Yang committed 2 years ago
9808501
vocab only
Michael Yang committed 2 years ago
bf54c84
directly use isvalidpart
Josh Yan committed 2 years ago
c365f19
e91d0ef
Update llama.cpp submodule to `5921b8f0` (#4731)
Jeffrey Morgan committed 2 years ago
22f5c12
added IsValidNamespace function
Josh Yan committed 2 years ago
298c996
0fc0cfc
replaced duplicate call with variable
Josh Yan committed 2 years ago
914f68f
bd1d119
96bc232