HN Mail
Subscribe
CPP
Show HN: Run Llama.cpp In-Process from Java with Project Panama FFM
6 points
|
0 comments
Apples to Apples: MLX vs. Llama.cpp for Gemma 4 12B on an M1 16GB
5 points
|
1 comments
Show HN: Will It Fit? – Opinionated Normal People Llama.cpp VRAM Estimator
4 points
|
1 comments
Show HN: Best setup local LLM found for a 5090 (llama.cpp fork + turboquant)
2 points
|
2 comments
Show HN: TurboPrefill – Multi-GPU prefill acceleration for llama.cpp
2 points
|
0 comments
Show HN: Micron: a high performance C++23 (re)implementation of Libc and the STL
6 points
|
3 comments
Show HN: LLMhop – A tiny, stateless router for LLMs with a NixOS module
2 points
|
0 comments