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