master
common : move up common_init() and fix Windows UTF-8 logs (#21176)
chore : correct typos [no ci] (#20041)
mtmd: qwen3 audio support (qwen3-omni and qwen3-asr) (#19441)
mtmd: Add DeepSeekOCR Support (#17400)
ci : add android arm64 build and release (#21647)
mtmd : remove libllava, remove clip-quantize-cli (⚠️ breaking change) (#13460)
model, mtmd: fix gguf conversion for audio/vision mmproj (#21309)
mtmd: refactor image preprocessing (#21031)
Fix locale-dependent float printing in GGUF metadata (#17331)
mtmd: add Gemma 4 audio conformer encoder support (#21421)
mtmd: add pos_0 to mtmd_image_tokens_get_decoder_pos (breaking change) (#22082)
mtmd: fix crash when sending image under 2x2 pixels (#21711)
model : support step3-vl-10b (#21287)
mtmd: correct mtmd_decode_use_mrope() (#22188)
mtmd: correct get_n_pos / get_decoder_pos (#22175)
requirements : update transformers/torch for Embedding Gemma (#15828)
mtmd : rename llava directory to mtmd (#13311)
mtmd : support Qwen 2.5 Omni (input audio+vision, no audio output) (#13784)
docs: listing qwen3-asr and qwen3-omni as supported (#21857)
