wolfgangK · HackerTrans

в прошлом месяцеdiscuss

I presume this works (will work) also for JupyterLite that is based on Pyodide ? Would be great if it helped getting the latest OpenCV-python version [0] and it's dnn goodies being available on a zero-install client side Notebook !

[0] https://news.ycombinator.com/item?id=48421858

wolfgangK

в прошлом месяцеdiscuss

OpenCV being in the list of Pyodide modules [0] was the biggest boon for my online teaching experience because remotely dealing with install woes (corporate proxies & cie) was a show stopper for regular Python. I'm hoping that they will package this new version and that it will bring the new neural networks engines goodies to the no-install crowd !

[0] https://pyodide.org/en/latest/usage/packages-in-pyodide.html

wolfgangK

4 месяца назадdiscuss

Nice ! My most pressing request for VSS would be efficient binary vectors : is this on the table ?

wolfgangK

11 месяцев назадdiscuss

Only those who don't care/know about prompt processing speed are buying Macs for LLM inference.

wolfgangK

11 месяцев назадdiscuss

For LLM inference, I don't think the PCIe bandwidth matters much and a GPU could improve greatly the prompt processing speed.

wolfgangK

11 месяцев назадdiscuss

Indeed, recent Flash Attention is a pain point for non CUDA.

wolfgangK

11 месяцев назадdiscuss

The idea is presumably that you would "sell" at an artificially low price.

wolfgangK

11 месяцев назадdiscuss

> The Soviets had the […]first woman,[…]

That is quite the claim !

wolfgangK

12 месяцев назадdiscuss

You forgot the "/s", or do you actually believe that it's capitalism's fault is a mother taking care of her children is "unpaid labor" ?

wolfgangK

12 месяцев назадdiscuss

"is hard" ≠ "sucks"

wolfgangK

в прошлом годуdiscuss

Most interesting ! Would you mind sharing the prompt and the resulting CLAUDE.md file ?

Thx !

wolfgangK

в прошлом годуdiscuss

IMO, it would be more interesting to have a 3-way comparison of price/performance between DeepSeek 671b running on :

1. M3 Ultra 512 2. AMD Epyc (which Gen ? AVX512 and DDR5 might make a difference in both performance and cost , Gen 4 or Gen 5 have 8 or 9 t/s https://github.com/ggml-org/llama.cpp/discussions/11733 ) 2. AMD Epyc + 4090 or 5090 running KTransformers (over 10 t/s decode ? https://github.com/kvcache-ai/ktransformers/blob/main/doc/en...)

comments