b9255

Release b9255 of llama.cpp features a Hexagon HMX quantized matmul rework (#23368), including updates to debug logging, dequantization logic using HVX vectors, removal of non-pipelined quantization operations, and improvements to HMX/power settings for Snapdragon devices. This release represents performance optimization work for Qualcomm Snapdragon hardware acceleration in the LLM inference framework.

Source: llama.cpp Releases | 2026-05-21