Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
chore: update models to use slice/chunk/chunksections (#12934)
333203d Michael Yang committed 1 year ago
app: remove source code for previous JavaScript-based macOS app (#13067)
54a76d3 Jeffrey Morgan committed 1 year ago
readme: fix incorrect header in community integrations (#13065)
f206357 Jeffrey Morgan committed 1 year ago
docs: rename api-reference.md back to api.md since redirect stopped working (#13056)
cb1cb06 Jeffrey Morgan committed 1 year ago
docs: fix openapi.yaml warnings, rename api.md to api-reference.md (#12904)
2d5e066 Jeffrey Morgan committed 1 year ago
docs/openapi: document that delete and copy responses are empty (#13055)
1596871 Bruce MacDonald committed 1 year ago
llm: Prefer dedicated GPUs over iGPUs when allocating memory
8bf3855 Jesse Gross committed 1 year ago
llm: Use Ollama engine memory layouts for both old and new engines
f560bd0 Jesse Gross committed 1 year ago
app/ui: do not send thinking to prevent errors with cloud provider
31361c4 Eva H committed 1 year ago
server: add logprobs and top_logprobs support to Ollama's API (#12899)
59241c5 Baptiste Jamin committed 1 year ago