Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
model/parsers: remove warning for missing <think> tag for qwen3-vl (#12713)
94f110b Jeffrey Morgan committed 1 year ago
renderers: add global flag for setting [img] tags (#12669)
65fb3ff Jeffrey Morgan committed 1 year ago
Revert "Workaround broken NVIDIA iGPU free VRAM data (#12490)" (#12642)
fe3ec8d Daniel Hiltgen committed 1 year ago
Merge pull request #12651 from ollama/drifkin/oai-conversion
201d937 Devon Rifkin committed 1 year ago
ml/backend/ggml: NVML fallback for unified memory GPUs (#12619)
8fafc8a Santosh Bhavani committed 1 year ago
envconfig: default to port 443 when connecting to ollama.com (#12617)
0d71305 Jeffrey Morgan committed 1 year ago
llm: Perform eviction when num_gpu is set with new estimates
3dcfd5f Jesse Gross committed 1 year ago