llama.cpp 0.9 stabilizes FP8, multi-sequence KV and broader audio paths
The signed llama.cpp 0.9.0 release adds OCP FP8 E4M3 quantization, flash-attention rows for efficient unified KV across multiple sequences and a batched tensor-copy API. It also adds Clover, Limite, Metis-1.6 and Mistral Large 4, expands speech with Chatterbox, Nemotron 3.5 Transcribe and Pocket TTS voices, and moves ggml to 0.29.0 with NCCL multi-node tensor parallelism.
Why it matters: A named stable checkpoint turns a fast prerelease stream into an adoptable boundary spanning quantization, serving, multimodal and distributed backends. Those breadth changes also make cross-model, cross-backend regression testing essential.