# llama.cpp adds FP16 activation support for Qualcomm Hexagon inference

This edition covers the gap since the 08:00 UTC report. llama.cpp release b11276 expands its Qualcomm Hexagon backend with FP16 activation kernels, improving support for on-device model execution on Snapdragon-class hardware.

## llama.cpp b11276 adds FP16 SILU, GELU, GEGLU and SWIGLU ops to Hexagon

llama.cpp release b11276 adds F16 support for several activation operations in its ggml-hexagon HTP backend, including SILU, GELU, GELU_QUICK, GEGLU and SWIGLU. The project says these paths were verified on-device on a QRD8850 using CPU-diffed correctness tests; SWIGLU_OAI builds across the supported DSP variants but was not yet covered by an on-device F16 test in this change. The practical effect is broader native FP16 execution for local models using the Qualcomm Hexagon backend, reducing a compatibility gap for Snapdragon-based inference. The contributor also reported token-generation benchmarks for Llama 3.2 1B and Qwen2.5 models, but those are project-reported measurements rather than independent performance results. 

[llama.cpp b11276 release](https://github.com/ggml-org/llama.cpp/releases/tag/b11276) · [llama.cpp PR #29209 — Hexagon f16 activation ops](https://github.com/ggml-org/llama.cpp/pull/29209)
