Skip to content

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

Commits on main

Revert "Enable Ollama engine by default" (#13481)
Daniel Hiltgen committed 11 months ago
abe67ac
1b308e1
flash attn: add auto mode for llama engine (#13052)
Daniel Hiltgen committed 11 months ago
bd6c1d6
model: force rope factor 1.0 for Gemma 3 (#13445)
Jeffrey Morgan committed 11 months ago
3af5d3b
Enable Ollama engine by default (#13443)
Daniel Hiltgen committed 11 months ago
7730895
tidy up lint warnings on windows (#13430)
Eva H committed 11 months ago
de9ecfd
docs: fix link to modelfile.mdx (#13220)
Alexander Gusak committed 11 months ago
93d45d7
Update README.md (#13373)
JJ committed 11 months ago
709f842
model: fix rotary embeddings for ministral 3 (#13432)
Jeffrey Morgan committed 11 months ago
2dfb744
openai: add v1/responses support (#13351)
Devon Rifkin committed 11 months ago
1eb5e75
embeddings: modified batch size (#13429)
nicole pardal committed 11 months ago
3475d91
template: add yesterdayDate helper function (#13431)
Jeffrey Morgan committed 11 months ago
48e78e9
routes: add logprobs in tool calls (#13238)
EasonLin committed 11 months ago
1c4e85b
cmd/bench: fix binary name in README (#13276)
Eloi Torrents committed 11 months ago
dac4f17
cmd/bench: fix options table in cmd/bench/README.md (#13216)
Julia Scheaffer committed 11 months ago
56b8fb0
nomic-embed-text:v2: model implementation (#13162)
nicole pardal committed 11 months ago
76f88ca
renderers/parsers: olmo3 instruct (#13383)
Parth Sareen committed 11 months ago
2bccf8c
parsers/renderers: olmo3 think (#13290)
Parth Sareen committed 11 months ago
0c5e5f6
fix: qwen2.5vl metal argsort
Michael Yang committed 11 months ago
d475d1f
model: add rnj-1 inference support (#13354)
Jeffrey Morgan committed 11 months ago
d2f334c