laya.cpp: standalone C++ inference with CUDA and Vulkan backends

Lars KarlslundSep 20119 stars

Ggml-based C++ runtime for all three checkpoints. Native tokenization, decision heads and JSON output; optimized FP16/BF16 CUDA on RTX with FP32 accumulation, plus Vulkan.

Open on GitHub

Preview of laya.cpp: standalone C++ inference with CUDA and Vulkan backends

Launch: Laya
Use case: Automation
Format: Repo
Source: github.com

Lars Karlslund

Curious Security Minded Octopus, freelance security consultant, loves Active Directory, finding holes in the cheese, co…

See all

mizorewww

@mizorewww · Sep 19

Validated Core ML ports of all Laya checkpoints. One short multilingual decision in 4.98 ms P50 on M3 Max with ANE FP16, at 2.78x better energy per decision than MLX FP16.

FluidInference

@FluidInference · Sep 21

Swift package that reads a form in a running Mac app through the Accessibility API, asks an on-device model what belongs in each field, and types it in. ~1 ms per decision.

Alex

@Alex_tra_memory · Sep 21

FluidInference ported Laya to CoreML with 99.5% of ops running on the ANE and benchmarked it at 3.7 ms per decision on an M5 Pro.

virajbhartiya

@virajbhartiya · Sep 21

Open on GitHub

laya.cpp: standalone C++ inference with CUDA and Vulkan backends

More built with Laya