Llama.cpp v1 Is Out

unofficialmerve 20 points 2 comments November 13, 2026
huggingface.co · View on Hacker News

Discussion Highlights (2 comments)

pvtmert

Well, also GH Release: - https://github.com/ggml-org/llama.cpp/releases/tag/v1.0.0 - https://news.ycombinator.com/item?id=50481715

SlavikCA

Recently I see quite a few changes, related to KV caches. Sounds like earlier the advice was: for coding, quantizing KV cache is bad, keep it at full F16/BF16. Sounds like now, 8 bit KV cache is ok for coding, but the question is which one? I see f8_e4m3, q8_0. Would be great to get more info about that.

Semantic search powered by Rivestack pgvector
12,728 stories · 120,417 chunks indexed