Skip to content

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

Commits on main

server: abort download on empty digest
Kyle Steere committed 1 year ago
9239a25
tools: remove newline stripping (#10869)
Parth Sareen committed 1 year ago
aea6fb9
tests: drop llama3.2-vision embedding tests (#10837)
Daniel Hiltgen committed 1 year ago
2307fc2
6623898
ml: Improve slog formatting for BackendMemory
Jesse Gross committed 1 year ago
f18e0cb
llama: add minimum memory for grammar (#10820)
Parth Sareen committed 1 year ago
884d260
ollamarunner: Memory usage reporting
Jesse Gross committed 1 year ago
73d6a82
ggml: Report graph memory for failed allocations
Jesse Gross committed 1 year ago
6db8a37
d950ff1
fix: mllama quality (#10807)
Michael Yang committed 1 year ago
adff143
fbe6ae2
integration: add qwen2.5-vl (#10815)
Daniel Hiltgen committed 1 year ago
fdd4d47
61aeaf7
win: detect background upgrade in progress (#10785)
Daniel Hiltgen committed 1 year ago
7359b02
feat: port qwen2 model (#10782)
Michael Yang committed 1 year ago
c890011
feat: qwen3 dense and sparse models (#10708)
Michael Yang committed 1 year ago
e0ed984
fix cmakelists (#10804)
Michael Yang committed 1 year ago
139f84c
chore: disable debug in binary libraries (#10788)
Michael Yang committed 1 year ago
375839e
69b2fe9
ml: add more rope options (#10775)
Michael Yang committed 1 year ago
9ed8bf1
fix llama and mistral3 models (#10774)
Michael Yang committed 1 year ago
ff180c3
3fe74fb
avoid kv truncation during create (#10761)
Daniel Hiltgen committed 1 year ago
1a0cfd0