llama.cpp v1.0.0: check API and server boundaries before treating the release as a speed upgrade
The release removes deprecated APIs, adds FP8 KV caches and MoE host-cache controls, and tightens server security. These are release facts, not an AraoAI performance reproduction.
Source: llama.cpp 官方发布说明
llama.cpp published v1.0.0 at 10:20 UTC on November 13, 2026, inside this reporting window. For local deployments, compatibility matters more than the milestone label. This report summarizes upstream release notes; AraoAI has not benchmarked the new release.
First, check bindings and rebuild integrations. The notes list removal of 35 deprecated functions and promotion of the NextN/speculative API into llama.h. A program using the C API should not assume that replacing a library is a sufficient upgrade test. CLI-only users and applications with native bindings face different risks.
Second, record weight precision and KV precision separately. OCP FP8 KV caches use -ctk/-ctv f8_e4m3 and support optional static scales. That changes attention-cache storage and computation, not the precision of model weights. It does not establish a universal speed gain or unchanged task performance. Measure memory, long-context behavior and throughput separately.
Third, the release adds host-memory MoE cache controls including CPU share. A deployment spanning VRAM and host RAM does not satisfy the assumptions of a simple total-weight/VRAM-bandwidth bound. Pin weights, engine build, cache policy, context, speculative settings and concurrency before comparing results.
Fourth, server changes tighten tool execution, private media URLs, CORS and DNS-rebinding boundaries. If an existing LAN integration stops working, inspect the relevant security options rather than disabling every restriction. Preserve the old binary and command line, validate text, images and tools on an isolated port, and only then switch. Release notes establish included functionality, not a measured benefit on every machine.
Source: https://github.com/ggml-org/llama.cpp/releases/tag/v1.0.0