ggml

Named by 2 kept items in this workspace.

Search every workspace for ggml. It matches the name as written, so it can find other things that share it.

The items that name it 2

Llama.cpp on a jailbroken PS5: run any GGUF model natively on the console
repo2026-10-16
Tensor library underlying llama.cpp that does the actual work.
Transformers now runs llama.cpp quants
article2026-09-22
Library providing the Metal kernels (quantization and attention kernels) that transformers reuses for packed GGUF inference; also provides the ggml-attn attention implementation.

All technologies in this workspace.