Qeravio
Canonical AI event

Llama.cpp updates get_alloc_size cache key and floors result at ggml_nbytes

The update includes support for Ubuntu s390x and macOS Apple Silicon with KleidiAI enabled.

26 Sept 20261 verified claims1 sources1 observations
What happened

The official source reports this update: b11180: rpc: include nb in the get_alloc_size cache key and floor the result at ggml_nbytes.

Why it matters

This official update documents a development concerning b11180: rpc: include nb in the get_alloc_size cache key and floor the result at ggml_nbytes. Its practical significance depends on the scope and evidence stated by the source.

What to watch next

Read the official source update and verify its stated scope, evidence and timing before acting on it.

Connected knowledge

Entities affected by this event

Llama Cppsubject
Continue this topic
infrastructureLegacy Vulkan build issue resolved with cooperativeMatrix API support added.26 Sept 2026infrastructureMetal FWHT kernels now support block widths up to 8192.26 Sept 2026infrastructureMetal kernels now split into per-dtype libraries.26 Sept 2026infrastructureHexagon updates DMA for contiguous dim1 CONCAT.26 Sept 2026infrastructureCUDA kernel fusion reduces kernel launches by 96 per batch on Qwen3.8-27B26 Sept 2026infrastructureLlama.cpp adds q5_k quant type support for Hexagon.26 Sept 2026
Evidence trail

Sources behind the event

llama.cpp official releasesb11180: rpc: include nb in the get_alloc_size cache key and floor the result at ggml_nbytes
Editorial presentation

Read the public story

Open story