It feels like a bit of history is missing... If ollama was founded 3 years before llama.cpp was released, what engine did they use then? When did they transition?

▲

wolvoleo 5 hours ago | parent | next [-]

I don't think that is the case. Llama.cpp appeared within weeks after meta released llama to select researchers (which then made it out to the public). 3 years before that nobody knew of the name llama. I'm sure that llama.cpp existed first

	▲	kgwgk 3 hours ago \| parent [-]
		> within weeks One week, really, if we consider the "public" availability. Llama announced: February 24, 2023 Weights leaked: March 3, 2023 Llama.cpp: March 10, 2023 (Ollama 0.0.1: Jul 8, 2023)

▲

Maxious 5 hours ago | parent | prev [-]

They spent several years in stealth mode but the initial release was llama.cpp.

Ollama v0.0.1 "Fast inference server written in Go, powered by llama.cpp" https://github.com/ollama/ollama/tree/v0.0.1

▲

em-bee 4 hours ago | parent [-]

They spent several years in stealth mode

doing what?

trying to build themselves what llama.cpp ended up doing for them?

	▲	saghul 4 hours ago \| parent [-]
		I asked myself the same question. Some other commenter mentioned above they started with some Kubernetes infrastructure thing and they pivoted later.