The story’s score and claims

Comments on No. 36 of 62 · GitHub · edition of Sunday 15 November 2026

Ggml v1.0.0

Summary

The ggml 1.0.0 release, published through the llama.cpp project, removes deprecated public API and legacy diagonal-mask ops, and adds YaRN truncation control and FP8 support. It also broadens performance work across CUDA, Metal, Vulkan, SYCL, OpenCL and WebGPU backends, including MoE fusion and FlashAttention paths.

Comments

Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules