tandr

thank you! That was quite educational.

Thank you!

by the looks of it... any front collision == instant death?

What would be these additional vllm flags, if you don't mind sharing?

I think they are talking about AWS dashboard, but I might be wrong.

I understand that the project is in his early stages, and documentation (README) is very much WIP. So, couple questions

    1. "SSD backed" - on-the-fly 100% time (like KVRocks), or requires same "save" like Redis does?
    2. (if it is like kvrocks) Do you have any perf numbers for DB sizes that are, say, 10x of RAM size?

Some simpler benchmark table would be great. May I suggest Ollama on base machine, Ollama with T1, Ollama with T1+T2 etc. on midsize and big models to compare token/sec?

Niklaus Wirth died in 2024, and yet I hope he is having a major I-told-you-so moment about people blaming Pascal's bounds checking to be unneeded and making things slow.

It works, but the best in me I cannot explain fully first 3 symbols. /*?sr/bin/env finds /usr by expanding *? to a first matching directory. But why not just /*usr/ instead?

Index Size

    Biscuit 277.09 MB
    Trigram 86 MB
    B-Tree  43 MB

Pretty much you exchange space for speed

Spotify just (last week or 2 weeks ago) introduced lossless compression (FLAC) and it sounds amazing.

Last decades? wipes the tear You surely forgot /s at end, I hope. The evil incarnation what is called "Samsung fridge" that I have in my kitchen required repairman's attention just 3 months after the purchase. And then every 3 months after. And children sacrifices, sorry - steam baths, for the ice maker every month or so.

Samsung appliances - never again.

PS. Repairman told me that Samsung have fixed already one of the problems my fridge has by the time he looked at it, kind of hidden recall and fix. Fridge's version (yes, they have versions) have advanced like 7 iterations already from the time I bought it. That means there were at least 7 serious design/manufacturing problems that they had to fix.

Thank you, a very heartwarming story indeed.

I think you just have coined a new saying - "Always invite Anna" sounds intriguing, and yet at the same time very descriptive.

How crazy will it drive my dog?

Red vs Blue?

I was, but I guess adding /s at the end in these cases is a requirement nowadays...

Or could it be (or to be a bit of devil's advocate) that Rust projects require only 2% (1/50) of manpower, comparing the same project using C++?

Pardon for the old meme here, but... "Pics, or did not happened!"?

Is it weird that internet companies do not have this kind of oversight?

Or you can configure it to use local ollama, and actually use it when needed

    browser.ml.chat.hideLocalhost: false
    browser.ml.chat.provider:  http://localhost:11434

> Apples don't fall far from the tree, indeed.

And one could say that they borrow from the tree some of their qualities. Sorry, couldn't resist.

I tried it as a FS for a data volume (200GB) on Linux a year ago, after reading how stable it is "now". The first hard crash made it unrecoverable no matter what I have tried. Never again.

   > I can't wait to travel to Mexico or Canada to get a vaccine!

But... how? I do remember times during COVID when you couldn't even get on the plane without proof of vaccine.

Thank you, I haven't watched the show. But by the sound of it - that logic and his "style" in general are not that far from what "real life" characters are arguing about.

    > And who's worth the most? Companies that lose money.

I am failing to see the logic in this, sorry.

The larger model (235b) on chat produced rather an impressive answer on a small coding task I gave it. But Qwen-30B-A3B gave a result for the same task worse than Qwen 2.5 does.

"Write a Golang program that merges huge presorted text files, just like sort -m does". Quite often models need "use heap" as guidance, but this time big model figured it out by itself.

Would you be kind and share some examples?

Will we ever remember that?...

I think you might've misspelled "ruining" a bit. It is ok, I think we have read you correctly anyway, at least I did.