llama.cpp releases

10 stories

llama.cpp releasesToolsb11786 ggml-cpu : compute f32 gelu_quick and geglu_quick without the fp16 table ( #30737 ) ggml-cpu : compute f32 gelu_quick and geglu_quick without the fp16 table ggml-cpu : keep the GGML_GELU_QUICK_FP16…

10.21

llama.cpp releases

llama.cpp releasesToolsb11787 sycl: collapse duplicate need_check launch bodies in mmq ( #30739 )

10.21

llama.cpp releasesToolsb11785 llama : scale moe down projection per expert token ( #30861 ) llama : scale moe down projection per expert token Replace the global amax rescaling for the MoE down projection with a per-expert-token…

10.21

llama.cpp releasesToolsb11784 Sycl iq3 crash fix ( #30604 ) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/58078930 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64…

10.21

llama.cpp releasesToolsb11782 server : fix usage.completion_tokens undercount with n > 1 ( #29486 ) Assisted-by: Copilot Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/58070419…

10.21

llama.cpp releasesToolsb11781 server : add POST /tts endpoint for TTS models ( #26603 ) mtmd: add audio out stream api add /tts endpoint add docs wire up mtmd_helper_model_can_chat upload speaker_ref via form-data expose seed to…

10.21

llama.cpp releasesToolsb11780 server: add realtime transcription API ( #30636 ) server: add realtime transcription API drop transcription_sessions proxy ws add docs server: let the API key middleware guard the websocket httplib…

10.21

llama.cpp releasesToolsb11778 model : support Nemotron-3(.5)-Embed ( #30877 ) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/58053681 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple…

10.21

llama.cpp releases

llama.cpp releasesToolsb11783: opencl: fix rope program build error with newer Clang (#30893) Newer versions of Clang diagnose an incompatible pointer type error when assigning a pointer to float to a pointer to half.

10.21

llama.cpp releases

llama.cpp releasesToolsb11779 refactor : move LFM2 shortconv and FFN blocks into a shared LFM base …

10.20

The name is the button.

An agent writes the code now, and a human thumb hovers over Accept all a hundred times a day. The honest question of this decade is what, exactly, you just accepted. So I read the diff.

Eight years as a backend engineer in Stockholm, back in Tokyo since 2023, and I still ship something small most nights, usually badly. My one rule: the only real review of a model is the thing you built with it. That is why there is no leaderboard on this site.

Around a hundred and forty sources come through — the labs' own posts, the papers, the tools, the runtimes and languages nobody is watching yet, the chip under the demo, and the newsletters people actually forward. What is moving gets counted so the week reads at a glance, and every few days I explain one mechanism in plain words.

A story here is a headline, a short excerpt, one image and the link to whoever wrote it. We never reproduce the post; the images belong to their authors. A post written in Japanese appears in Japanese, exactly as it was published, and the link goes to the original.

— Yuki Halvorsen, Tokyo