Open-weight & owned stack · Quantization efficiency

llama.cpp fixes Vulkan tensor handling

Sep 28, 2026, first seen via Training & inference tooling releases

llama.cpp release b11224 fixed Vulkan batch-stride and buffer-range handling for strided tensors and added regression tests.

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

More in Open-weight & owned stack

Aikido releases open-weight cybersecurity modelSep 28 Developer releases Apple Silicon LLM wrapperSep 28 Fireworks releases token-efficient Ember-1 modelSep 28 Z.ai releases MIT-licensed GLM 5.2Sep 28 llama.cpp accelerates vision prompt processingSep 28