Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
cmd: capitalize Ollama in serve command help text (#13965)
f92e362 Seokrin Taron Sung committed 9 months ago
cmd/config: use envconfig.Host() for base API in launch config packages (#13937)
7b62c41 Gabe Goodhart committed 9 months ago
parsers/ministral: fix nested tool call parsing by counting brace nesting (#13905)
e0f0379 Gyungrai Wang committed 9 months ago
glm4moelite: fix attention scale calculation (#13893)
a1ca428 Jeffrey Morgan committed 10 months ago
glm4moelite: quantize more tensors to q8_0 and avoid double BOS token (#13891)
1675086 Jeffrey Morgan committed 10 months ago
README: Update the "Ollama for ruby" to the most popular and maintained ruby gem. (#13855)
b44f563 Stillhart committed 10 months ago
llama: fix fattn-tile shared memory overflow on sm_50/52 (#13872)
912d984 Jeffrey Morgan committed 10 months ago
Re-apply "model: add MLA absorption for glm4moelite" with fix (#13870)
6473733 Jeffrey Morgan committed 10 months ago
Revert "model: add MLA absorption for glm4moelite (#13810)" (#13869)
2eda97f Jeffrey Morgan committed 10 months ago
cmd: ollama config fix droid model name configuration (#13856)
771d928 Parth Sareen committed 10 months ago
x/imagegen: respect stream=false in /api/generate (#13853)
862bc0a Jeffrey Morgan committed 10 months ago
cmd: `ollama config` command to help configure integrations to use Ollama (#13712)
199c41e Parth Sareen committed 10 months ago
x/imagegen: replace memory estimation with actual weight size (#13848)
3b3bf6c Jeffrey Morgan committed 10 months ago
fix: handle Enter key pressed during model loading (#13839)
f52c21f Parth Sareen committed 10 months ago
x/imagegen: remove qwen_image and qwen_image_edit models (#13827)
b5d0f72 Jeffrey Morgan committed 10 months ago
x/imagegen: respect OLLAMA_MODELS for manifests and blobs (#13797)
d6dd430 next-n committed 10 months ago