Ggml v1.0.0
Comments
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
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.