0 stories · 7d·6 sources covering·3 active storylines
What this is
Llama is Meta's family of open-weight large language models. shipfeed tracks every Llama release, new generation, weight drop, and the ecosystem of fine-tunes built on it.
IBM launched Red Hat AI Inference on IBM Cloud for real-time AI inferencing with models like Granite 4.0 and Llama 3.3, and Red Hat OpenShift Virtualization Service, both GA on May 22, 2026.
NVIDIA researchers introduced X-Token, a projection-guided cross-tokenizer knowledge distillation method that improves performance on smaller models like Llama-3.2-1B.
llama: limit max outputs of `llama_context` (#23861) llama: save more VRAM by reserving n_outputs == n_seqs when possible add n_outputs_per_seq move n_outputs_max to server-context change ubatch to batch everywhere…