Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
auth: check the permissions on the private key to see if it's readable (#12336)
eb0a5d4 Patrick Devine committed 1 year ago
server: skip parsing initial <think> if provided in the prompt for /api/generate (#12289)
9b8187b frob committed 1 year ago
refactor: use the built-in max/min to simplify the code (#12280)
05d5345 russcoss committed 1 year ago
Merge pull request #12248 from ollama/drifkin/qwen3-coder-parsing
fa1c987 Devon Rifkin committed 1 year ago
Revert "runner: simplify parser entrypoints in runner (#12233)"
9d56e63 jmorganca committed 1 year ago
cuda: remove compression for better compatibility (#12259)
e4ce683 Daniel Hiltgen committed 1 year ago
ollamarunner: Suppress stack trace during memory allocation
2621412 Jesse Gross committed 1 year ago
llm: Don't try to load split vision models in the Ollama engine
aba1575 Jesse Gross committed 1 year ago