Riscv
Benchmarking llama.cpp on SpacemiT K3: RISC-V AI Cores vs Standard RVV (Part 4)
TL;DR SpacemiT's K3 has two core types: X100 (general-purpose, vlen 256) and A100 ("AI cores", vlen 1024). Standard llama.cpp runs 2.3x …
Running a Local LLM on RISC-V: Building llama.cpp on a Banana Pi F3 (Part 1)
TL;DR I built llama.cpp from source on a Banana Pi F3 (SpacemiT K1, riscv64), ran TinyLlama 1.1B, and got an OpenAI-compatible API server running at …
Building WASI SDK on RISC-V: Self-Hosted WebAssembly Development on a Banana Pi F3
Photo by Quang Vuong on Pexels In my previous article, I ran WebAssembly containers on a RISC-V board and hit a wall: WASI SDK, the standard …
A glimpse of the future
A glimpse of the future You’ve all seen it before: the bitter sting of botched predictions. Flying cars, nuclear ovens in the kitchen, killer robot …
miniJen and RISC-V
Short Introduction What is miniJen? It’s the Jenkins multi-cpu-architectures smallest instance known to this day. It’s composed of a 4 arm) …
miniJen is alive!
miniJen The Jenkins multi-architecture CPU instance What is that contraption? Nope, it’s not a robot of some sort, it won’t move by itself. It’s not …
Running a 70B LLM on Pure RISC-V: The MilkV Pioneer Deployment Journey
When the 40GB download completed and the model loaded into memory, I wondered: would a 70-billion parameter language model actually run on a RISC-V …
