Dharshaneshwaran

Dharshaneshwaran

GitHub

Repositories

1

Total stars

56

Top repositories

Pools consumer laptops into one local runtime for Meta Llama models. Measures the free VRAM each machine reports, splits the model across CUDA and Metal devices through llama.cpp RPC, and rebuilds the pipeline when a worker drops out.

Created Oct 2026

cuda distributed-inference fault-tolerance gguf golang
Total 56