llama.cpp releases

10 stories

llama.cpp releasesToolsb12087 mtmd : add Nemotron 3.5 Transcribe support ( #31471 ) mtmd : add Nemotron 3.5 Transcribe support Assisted-by: Claude convert : fix vocab of draft models for Nemotron-H targets Assisted-by: Claude…

11.04

llama.cpp releasesToolsb12086 qwen4exp: write the conv state tail without an intermediate cont ( #31443 ) build_conv_state_at makes a contiguous copy of the conv input tail before writing it into the recurrent state, so every GDN…

11.04

llama.cpp releasesToolsb12084 model : record layer inputs in LFM3 for spec dec ( #31598 ) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/63354471 macOS/iOS: macOS Apple Silicon (arm64)…

11.03

llama.cpp releasesToolsb12083 ggml: avoid signed overflow in ggml_roll bounds check ( #30375 ) ggml_roll validated each shift with abs(shift), but abs(INT_MIN) is signed integer overflow UB evaluated before the bounds check runs.

11.03

llama.cpp releasesToolsb12081 cuda: potential fix for Q8_1 correction sum ( #31247 ) cuda: potential fix for Q8_1 correction sum Update ggml/src/ggml-cuda/quantize.cu Co-authored-by: Gaurav Garg gaugarg@nvidia.com addressed…

11.03

llama.cpp releasesToolsb12080 cuda : gather batched tensor reads into mapped host memory (PR to master) ( #31391 ) cuda: gather batched tensor reads into mapped host memory Assisted-by: Codex add comments Assisted-by: Codex…

11.03

llama.cpp releases

llama.cpp releasesToolsb12079 Add nccl support for multi-node tensor parallelism ( #28967 ) Add a backend interface for collectives across ranks running in separate processes, implement it in the CUDA backend using NCCL, and use…

11.03

llama.cpp releasesToolsb12078 tools : reject mismatched shards in GGUF split merge ( #31579 ) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/63239877 macOS/iOS: macOS Apple Silicon…

11.03

llama.cpp releasesToolsb12077 meta: support GLM-5.3 next sm tensor ( #30499 ) meta: support GLM-5.3 next sm tensor glm5-next : cont q_absorbed for -sm tensor with non-unified KV meta : keep GGML_OP_ARANGE in ggml.h order…

11.03

llama.cpp releasesToolsb12088 model : enable NVFP4 LFM3 ggufs ( #31608 )

11.03

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