Ggml v1.0.0
cobychapple
134 points
21 comments
November 14, 2026
Related Discussions
Found 5 related stories in 138.8ms across 12,728 title embeddings via pgvector HNSW
- Llama.cpp v0.1.0 satvikpendem · 42 pts · August 17, 2026 · 61% similar
- Llama.cpp v1 Is Out unofficialmerve · 20 pts · November 13, 2026 · 56% similar
- Llama.cpp hits v1.0 with a native app for macOS shubham0204 · 14 pts · November 14, 2026 · 54% similar
- vLLM v0.28.0 mrrrcs · 106 pts · August 29, 2026 · 49% similar
- GLM-5.3 is now open-weight jeudesprits · 646 pts · August 28, 2026 · 48% similar
Discussion Highlights (7 comments)
evilelectron
Awesome! ggml and llama.cpp are the Linux of the AI world. Driving local inference one bit at a time. Wishing you unlimited power and may you never see a day of low battery. Respect and Love. Keep it up.
palad1n
I prefer this entry point: https://github.com/ggml-org/ggml
kodoman
Long time llama.cpp user (and user of other ggml based AI programs) running on my crappy AMD card that only supports vulkan and it's usable thanks to GGML and llama.cpp, great program great project.
om8
Imagine naming a library after yourself. > GGML is a C library for machine learning (ML) - the "GG" refers to the initials of its originator (Georgi Gerganov). https://github.com/rustformers/llm/blob/main/crates/ggml/REA...
jacquesm
What is really impressive about this project and llama.cpp as well is that they keep finding new ways to speed up the code on the same hardware. Every time I upgrade (once a month or so) there is usually a 5 to 10% speed boost.
snvzz
Not just legacy hardware, but also ready for the immediate future, with RISC-V support. Congrats for 1.0.0.
hizlikovboy27
In my opinion, this is a genuine engineering product. LLM.cpp, the savior of our difficult times...