llama.cpp v0.9.0

## Overview This release adds OCP FP8 E4M3 quantization support, a new op that makes the unified KV cache efficient for multi-sequence inference, and a generic batched tensor copy API. Four new architectures are supported (Clover, Limite, Metis-1.6 and Mistral Large 4), audio generation and transcription expand with Chatterbox TTS, Nemotron 3.5 Transcribe and predefined Pocket TTS voices, and the Gemma 4 E2B/E4B models get major prefill optimizations. is updated to v0.29.0, bringing FP8 E4M3, flash attention rows, NCCL-based multi-node tensor parallelism and performance work across the CPU, CUDA, SYCL, Metal, Vulkan, OpenCL and Hexagon backends. The server and UI receive a round of fixes and refinements. ### Highlights - Quant: OCP FP8 E4M3 tensor type (saturating mode) with conversion helpers and a new ftype ([#27512](https://github.com/ggml-org/llama.cpp/pull/27512)) - llama: - more efficient unified KV for multi-seq, restoring non-unified KV prefill performance ([#29510](https://github.com/ggml-org/llama.cpp/pull/29510)) - ggml: batched tensor copy API (//) superseding the…