The sphere packing problem in dimension 8 · HackerPapers discussions

The sphere packing problem in dimension 8 — HN submission

Mon, 01 Jun 2026 21:17:26 GMT

Show HN: Glq LLM quantization using E8 lattice

I have with the help of AI create an open source method of E8 LLM code book quantization library called glq. I was interested in creating Glq as a PC gamer and devops, interested in both LLMs and AI. The current high RAM prices and LLM resource usage also inspired me to write glq. A question arises could you try and squeeze more out a gaming GPU with limited VRAM size by using alternative LLM compression methods? Glq is effective compared to other LLM quantization algorithms at between 2-bits per weight up to 4 bits per weight. The effectiveness of glq at low bits per words is due to the…

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

The sphere packing problem in dimension 8 — mentioned by stncls

Wed, 06 Jul 2022 07:29:29 GMT

No no no, she is legit, no doubt here. She was a star way before the current events. She solved a long-standing open problem in fundamental maths. This is the holy grail in maths research. The main resulting paper is single-author, so there is no doubt who did the work. She got her PhD from Bonn in 2013 and became a full prof at EPFL in 2018 (in EU this type of progression takes 10-20 years, and this is extremely impressive even by US standards). It was very clear to everyone at that time that she would be big. Or just look at the paper: https://arxiv.org/abs/1603.04246 you can't fake that…

Paper and discussion history. A mention is not an endorsement.

The sphere packing problem in dimension 8 — mentioned by ecma

Thu, 31 Mar 2016 07:27:34 GMT

The paper [0] was linked, the article gave context to the problem and outlined the approach. What more do you want? [0] http://arxiv.org/abs/1603.04246

Paper and discussion history. A mention is not an endorsement.