Heykuki News

TopNewBestAskShowJobs
TopNewBestAskShowJobs
1.
Fixed a llama.cpp bug silently disabling Vulkan GPU on all 32-bit ARM devices
3 points
perinban
2 months ago
discuss
2.
Show HN: Running LLM on smartwatch – found llama.cpp loading model twice in RAM
1 point
perinban
2 months ago
discuss
3.
MetaXuda – 1.1 Tops GPU Runtime for Apple Silicon ML (Rust and Metal) (github.com/Perinban)
2 points
perinban
5 months ago
1 comment