Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
Merge pull request #5440 from ollama/mxyng/messages-templates
6bbbc50 Michael Yang committed 2 years ago
server: fix model reloads when setting `OLLAMA_NUM_PARALLEL` (#5560)
e4ff732 Jeffrey Morgan committed 2 years ago
llm: remove ambiguous comment when putting upper limit on predictions to avoid infinite generation (#5535)
53da2c6 Jeffrey Morgan committed 2 years ago
sched: don't error if paging to disk on Windows and macOS (#5523)
0ee8761 Jeffrey Morgan committed 2 years ago
llm: add `-DBUILD_SHARED_LIBS=off` to common cpu cmake flags (#5520)
4607c70 Jeffrey Morgan committed 2 years ago
llm: statically link pthread and stdc++ dependencies in windows build
f1a379a jmorganca committed 2 years ago
llm: add `COMMON_DARWIN_DEFS` to arm static build (#5513)
e0348d3 Jeffrey Morgan committed 2 years ago
llm: fix missing dylibs by restoring old build behavior on Linux and macOS (#5511)
2cc854f Jeffrey Morgan committed 2 years ago