Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
MLX: add header vendoring and remove go build tag (#14642)
10e51c5 Daniel Hiltgen committed 8 months ago
mlx: get parameters from modelfile during model creation (#14747)
3e06bde Patrick Devine committed 8 months ago
app: auto update should be enabled when reset to defaults (#14741)
6be2de8 Eva H committed 8 months ago
x/mlxrunner: replace sampler interface chain with single stateful Sampler (#14652)
d126467 Patrick Devine committed 8 months ago
cloud_proxy: handle stream disconnects gracefully (#14685)
afb4c62 Devon Rifkin committed 8 months ago
Reapply "don't require pulling stubs for cloud models" again (#14608)
4eab60c Jeffrey Morgan committed 8 months ago
parsers: repair unclosed arg_value tags in GLM tool calls (#14656)
1af850e Bruce MacDonald committed 8 months ago
cmd: override stale entries for context window pi (#14655)
9b0c7cc Parth Sareen committed 8 months ago
cmd/config: fix cloud model limit lookups in integrations (#14650)
9896e36 Parth Sareen committed 8 months ago
cmd: use native Ollama API endpoint for OpenClaw (#14649)
15732f0 Bruce MacDonald committed 8 months ago
Revert "Reapply "don't require pulling stubs for cloud models"" (#14606)
39982a9 Jeffrey Morgan committed 8 months ago
Add qwen3.5-next-moe support to MLX runner and models (#14417)
e9f6ea2 Patrick Devine committed 8 months ago
Reapply "don't require pulling stubs for cloud models"
799e51d Jeffrey Morgan committed 8 months ago
model/renderers: fix glm-ocr image tags in renderer prompts (#14584)
e8fcb29 Victor-Quqi committed 8 months ago
Revert "don't require pulling stubs for cloud models (#14574)" (#14596)
97d2f05 Jeffrey Morgan committed 8 months ago
cmd/opencode: rename provider from "Ollama (local)" to "Ollama" (#14566)
a3093cd Parth Sareen committed 8 months ago