Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
partial offloading: allow flash attention and disable mmap (#4734)
a50a87a Jeffrey Morgan committed 2 years ago
Merge pull request #4594 from dhiltgen/doc_container_workarounds
0fc0cfc Daniel Hiltgen committed 2 years ago
Fix OLLAMA_LLM_LIBRARY with wrong map name and add more env vars to help message (#4663)
a03be18 Lei Jitang committed 2 years ago