Skip to content

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

Commits on main

9e125d8
gguf: fix write order (#11068)
Michael Yang committed 1 year ago
a6fbfc8
9f8a18e
feat: incremental gguf parser (#10822)
Michael Yang committed 1 year ago
6b04cad
feat: uneven splits (#11048)
Michael Yang committed 1 year ago
45f5635
skip tokenizer.model if possible (#11050)
Michael Yang committed 1 year ago
0dabb4e
use nn.Linear in place of ml.Tensor (#11049)
Michael Yang committed 1 year ago
2e77aa1
deaabe2
readme: update quickstart link text to Gemma 3
Jeffrey Morgan committed 1 year ago
af21a5a
readme: update quickstart example to Gemma 3
Jeffrey Morgan committed 1 year ago
f63d7f6
mac: handle "keep" named apps (#11031)
Daniel Hiltgen committed 1 year ago
82ad1db
spawn desktop quickly (#11011)
Daniel Hiltgen committed 1 year ago
feeabda
docs: update link to AMD drivers in linux.md (#10973)
Krzysztof Jeziorny committed 1 year ago
fc03096
launch app hidden (#10962)
Daniel Hiltgen committed 1 year ago
a8ed68b
win: handle more than 2048 processes (#10997)
Daniel Hiltgen committed 1 year ago
2ae65ae
move thinking logic into its own package (#10990)
Devon Rifkin committed 1 year ago
a3b6886
docs: fix typo in development.md (#10998)
Hunter Wittenborn committed 1 year ago
c6a6d72
export ThinkingParser
Devon Rifkin committed 1 year ago
0683efa
ggml: Export GPU UUIDs
Jesse Gross committed 1 year ago
aaa7818
f15ffc4
add thinking support to the api and cli (#10584)
Devon Rifkin committed 1 year ago
5f57b0e
client: add request signing to the client (#10881)
Patrick Devine committed 1 year ago
aa25aff