Skip to content

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Commits on main

1b45aa1
fix data races in progress and sched (#18319)
Daniel Hiltgen committed 2 months ago
b5d373f
9ef6c19
openai: use tsc_ prefix for tool search call IDs (#18296)
Jeffrey Morgan committed 2 months ago
3b5ab1f
app: harden Codex desktop proxy handling (#18244)
Parth Sareen committed 2 months ago
83ed7d9
b043d89
43e6670
ci: bound and cache the macOS MLX payload build (#18240)
Daniel Hiltgen committed 2 months ago
d3efc63
app: add Ollama to ChatGPT Desktop (#18236)
Eva H committed 2 months ago
87b9f9e
openai: add Codex compaction support (#18224)
Parth Sareen committed 2 months ago
3f77cb6
openai: add client tool search support (#18223)
Parth Sareen committed 2 months ago
cf8b605
docs: fix broken download links in app README
Lichao Chen committed 2 months ago
631900d
4986e92
gemma4: image and audio input support
Jesse Gross committed 2 months ago
b79067b
3ffc9a6
ba064c3
mlx: fix mtp_test unit test (#18203)
Daniel Hiltgen committed 2 months ago
882387a
llama.cpp: version bump b10760 (#18199)
Daniel Hiltgen committed 2 months ago
b1d1ccc
Report cached prompt tokens (#17943)
Daniel Hiltgen committed 2 months ago
855f4bf
ci: wire up MLX unit tests for PR runs (#17022)
Daniel Hiltgen committed 2 months ago
e5e4377
llama.cpp: version bump b10729 (#18160)
Daniel Hiltgen committed 2 months ago
5ec5804
MLX, MLX-C: version bump (#18080)
Daniel Hiltgen committed 2 months ago
3ba380d
Honor model generation defaults (#16471)
Daniel Hiltgen committed 2 months ago
f348c7e
build: go deps (#18161)
Daniel Hiltgen committed 2 months ago
205a042
mlx: dedup dependency files (#18159)
Daniel Hiltgen committed 2 months ago
ef117cf
e37a00a