CPP

I patched llama.cpp to gain 20% prompt processing TPS. Help me make a PR
6 points | 2 comments

As; HN: I was curious why MTP affects PP TPS in llama.cpp. My PoC recovers it?
4 points | 1 comments

Transcribe.cpp – ggml based transcription engine
4 points | 0 comments

TurboPrefill: 2.7× faster than llama.cpp Pipeline Parallel on Llama-3-70B
3 points | 0 comments

Llama.cpp flags auto-tuning tool
3 points | 0 comments

Show HN: Run AI chat, image gen, vision, and voice offline on your Mac
10 points | 3 comments

Show HN: Sipp – Run small local LLMs in browser 3x faster
5 points | 3 comments