Skip to content

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

Commits on main

Report better error on cuda unsupported os/arch
Daniel Hiltgen committed 2 years ago
ce3c93b
Explain font problems on windows 10
Daniel Hiltgen committed 2 years ago
6c2129d
Ensure amd gpu nodes are numerically sorted
Daniel Hiltgen committed 2 years ago
7c2a157
llm(llama): pass rope factors (#5924)
Michael Yang committed 2 years ago
bb46bbc
Fix Embed Test Flakes (#5893)
royjhan committed 2 years ago
ac33aa7
Better explain multi-gpu behavior
Daniel Hiltgen committed 2 years ago
830fdd2
Update README.md to add LLMStack integration (#5799)
Ajay Chintala committed 2 years ago
a6cd8f6
Merge pull request #5864 from dhiltgen/bump_go
Daniel Hiltgen committed 2 years ago
c780892
Bump Go patch version
Daniel Hiltgen committed 2 years ago
5d604ee
fix dupe err message (#5857)
Josh committed 2 years ago
db0968f
Enable windows error dialog for subprocess startup
Daniel Hiltgen committed 2 years ago
e12fff8
update api.md
Michael Yang committed 2 years ago
9b60a03
docs
Michael Yang committed 2 years ago
83a0cb8
api embed docs (#5282)
royjhan committed 2 years ago
c064823
convert: capture `head_dim` for mistral (#5818)
Jeffrey Morgan committed 2 years ago
d835368
comments
Michael Yang committed 2 years ago
85d9d73
cleanup tests
Michael Yang committed 2 years ago
78140a7
uint64
Michael Yang committed 2 years ago
1954ec5
int
Michael Yang committed 2 years ago
0f19101
string
Michael Yang committed 2 years ago
e2c3f6b
keepalive
Michael Yang committed 2 years ago
8570c1c
bool
Michael Yang committed 2 years ago
55cd3dd
models
Michael Yang committed 2 years ago
66fe77f
origins
Michael Yang committed 2 years ago
d1a5227
host
Michael Yang committed 2 years ago
4f1afd5
rfc: dynamic environ lookup
Michael Yang committed 2 years ago
35b89b2
Merge pull request #5854 from dhiltgen/win_exit_status
Daniel Hiltgen committed 2 years ago
5784c05
Merge pull request #5855 from dhiltgen/remove_max_vram
Daniel Hiltgen committed 2 years ago
f14aa54
Update llama.cpp submodule commit to `d94c6e0c` (#5805)
Jeffrey Morgan committed 2 years ago
f8fedbd