Tech Meridian ← ENTITY INDEX
PROMY MERIDIAN RU

TOPIC · ENTITY #6216

ggml

Related event timeline, sources and context from the news index.

EVENT TIMELINE

2

CODING · 1 SOURCE · Hugging Face

Hugging Face releases llama.cpp and ggml libraries v1.0.0, commits to stable API/ABI

The llama.cpp project and its underlying engine ggml published version 1.0.0, signaling a commitment to stable API and ABI boundaries and semantic versioning for ggml-org projects. The announcement highlights cross‑platform, quantized inference on diverse hardware (from consumer PCs to servers), expanded backend support, CI investments using HF Buckets and HF Jobs, and accompanying Llama desktop apps for macOS and Windows.

7.0

MODELS · 1 SOURCE · Hugging Face

Transformers adds GGUF (llama.cpp quant) support on main

Hugging Face's transformers (main branch) can now load and run GGUF quantized checkpoints using llama.cpp/ggml kernels, aiming for efficient local inference (initially optimized for Apple Silicon and Qwen3.5 models). The integration also enables serving GGUF checkpoints via transformers-serve and falls back to dequantization if compatible kernels are unavailable.

7.0