Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
mlx: preserve generation panics during cleanup (#18886)
997b98f Daniel Hiltgen committed 1 month ago
server: fix multimodal embedding load with small num_ctx (#18973)
a527652 Jeffrey Morgan committed 1 month ago
docs: Merge pull request #18963 from ollama/security.md_update
0473039 Anna Rahn committed 1 month ago
launch: populate Codex model picker with installed Ollama models (#18887)
6eaad72 Parth Sareen committed 1 month ago
mlx: compact restored recurrent state after speculative rollback (#18955)
a5b659e Daniel Hiltgen committed 1 month ago
server: reuse verified manifests and loaded models in inference routes (#18947)
9d35332 Daniel Hiltgen committed 1 month ago
mlx: read candidate logits in float32 for quantized heads
c1c5362 Jeffrey Morgan committed 1 month ago
llm: support multimodal embeddings through llama-server
0c21bcf Jeffrey Morgan committed 1 month ago
llama: update to b11521 and use native decision support
adc4aae Jeffrey Morgan committed 1 month ago
decision: align request validation and option descriptions
1ba3c76 Jeffrey Morgan committed 1 month ago
server: skip local model compatibility migration (#18908)
eab97e9 Jeffrey Morgan committed 1 month ago
launch: suppress Claude Code connector warning for Ollama (#18878)
021cda5 Eva H committed 1 month ago
Merge pull request #18855 from ollama/launch-claude-max-context-tokens: Set CLAUDE_CODE_MAX_CONTEXT_TOKENS to model's context length
b061384 J Berg committed 1 month ago
server: hide duplicate and downgrade guards from list (#18874)
531946e Daniel Hiltgen committed 1 month ago
Set CLAUDE_CODE_MAX_CONTEXT_TOKENS to whatever the models context window is
c77b81c Jonathan Berg committed 1 month ago
mlx: drop carried metal residency patch now that it is upstream (#18854)
cf2a313 Daniel Hiltgen committed 1 month ago
Merge pull request #18233 from chenlichao/fix/app-readme-download-links
f9f4af6 Anna Rahn committed 1 month ago