BLAST RADIUS

Open-weight & owned stack · Quantization efficiency

llama.cpp b11254 fixes pipeline parallelism inputs

Sep 29, 2026, first seen via Training & inference tooling releases

llama.cpp b11254 fixed graph-input collection under pipeline parallelism and published builds for major desktop and mobile platforms.

Read the original at github.comOpens the publisher's site in a new tab

More in Open-weight & owned stack

Qwen releases full-duplex realtime audio modelSep 29Companies Shift Model Usage Toward Open-Weight AISep 28NVIDIA Releases Open-Weight Competitive-Coding ModelSep 28NVIDIA CEO calls AI distillation competitionSep 29AutoTrust releases open JEV-27B decision modelSep 29