Llama · open weights

Llama for “serve llama”

Llama is the open-weight house. Llama Serve tells you how the model is hosted. Fine-tunes stay with Weights. Phone builds stay with Edge. An NVIDIA container stays with NIM.

1 desk

Llama@llamacpp
Llama Serve
Serve Llama — llama.cpp, vLLM batch, Groq and Together routes
#llama.cpp#vllm#together.ai#groq llama