Could you explain the pseudo code in your equations page? Is the second approxMu... | Hacker News

Hacker News new | past | comments | ask | show | jobs | submit

login

gcy 8 months ago | parent | context | favorite | on: Show HN: Speeding up LLM inference 2x times (possi...

Could you explain the pseudo code in your equations page? Is the second approxMul call a typo (also the capitalized V)?

def precompute(W): W = W.T probes = get_probes(W) W_idx, W_val = sortMatrixRows(W)

def approxMul(v, W_idx, W_val, probes): cutoff_chart = v * probes cutoff = topK(cutoff_chart, effort) approxMul(V, W_idx, W_val, cutoff)

kolinko 8 months ago [–]

oh, thanks, I fixed it. No idea what I meant there originally.

There are still a few typos on the page, I'll be fixing them tomorrow - it's midnight now, and my mental batteries are slowly drying out :)

mijoharas 8 months ago | [–]

Did you deploy your changes? I just refreshed and that is still there on the page[0].

[0] https://kolinko.github.io/effort/equations.html

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact