Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
server: classify mmproj GGUFs as projector layers (#16472)
5f56a28 Jeffrey Morgan committed 5 months ago
llama: add laguna (poolside) arch via a llama.cpp patch under llama/c… (#16396)
c952708 Daniel Hiltgen committed 5 months ago
llm: detect llama-server load stalls from output (#16427)
b7b7fa0 Daniel Hiltgen committed 5 months ago
llm: include cached prompt tokens in llama-server counts (#16428)
35fa277 Daniel Hiltgen committed 5 months ago
cmd/launch: fix configure cline ollama provider via providers.json (#16352)
0038149 Eva H committed 5 months ago
convert: fixes for qwen3next model conversion (#16354)
0e93ccc Patrick Devine committed 5 months ago
model: improvements to laguna-xs.2 parser/renderer (#16362)
e7766a4 Jeffrey Morgan committed 5 months ago
llama: handle Gemma 4 and LFM2 BOS override in llama server (#16367)
be7de10 Jeffrey Morgan committed 5 months ago
runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031)
9db4bdb Daniel Hiltgen committed 5 months ago
mlx: fix reported information in `ollama show` (#16289)
f63eea3 Patrick Devine committed 6 months ago