xfalcox

Joined 13 years ago

Karma

1,042

Submissions

317

Member since

Nov 7

[ my public key: https://keybase.io/falcofantastic; my proof: https://keybase.io/falcofantastic/sigs/_PKYsKf2wmCyt834lEh6N4POje9RoICd3Ta7qezTzJE ]

View on Hacker News

Recent submissions

Comment · 9 days ago

I've been using herdr and this looks like a v2 of it. Will give it a try.

Comment · 28 days ago

Doesn't the article covers the speed part by showing that Qwen 3.6 35A3B has lower latency and same accuracy?

Comment · 2 months ago

Yeah, DeepSeek 4 Flash on vLLM has been an adventure indeed. It finally stabilized for me on 2 x H200 using a commit a few days before 0.28, so this release should be good for you.

Comment · 2 months ago

Have you tried running it on a single 5090? Dual 5090 require https://github.com/aikitoria/open-gpu-kernel-modules for higher perf. Are you using TP?

Comment · 3 months ago

I'm wondering the same! How that article has no links is beyond me.

Comment · 3 months ago

Question to the OP, have you tested this on a machine where the entire model and context fit in RAM ?

Comment · 3 months ago

README covers that

https://github.com/JustVugg/colibri#ssd-wear-warning

Comment · 5 months ago

Given my dev machine has 32GB of RAM and 32GB of VRAM that sits mostly idle when I'm not running AI models, this is not that bad of an idea.

Comment · 7 months ago

Comparing a model you can downloads weights for with an API-only model doesn't make much sense.

Comment · 7 months ago

Our CEO did that at our company and found 33 CVEs. Rails also did that and found 7 or 8.

Comment · 9 months ago

I just made a new installer for Discourse on CharmRuby, now I gotta check this out and see if porting is feasible. Hopefully this reduces the app size, that is quite large with CharmRuby

Comment · 9 months ago

That is a great fit for the GIF integration in Discourse.

I was able to quickly add support for it at https://github.com/discourse/discourse-gifs/pull/107

Love to see WEBP support. Do you plan on adding support for AVIF?

Also, this is used by many Discourse sites, we should talk.

Comment · 9 months ago

First time I was in San Francisco and someone introduced themselves like that, going even beyond, was indeed a super weird experience being a brazilian.

Comment · 11 months ago

We have vLLM for running text LLMs in production. What is the equivalent for this model?

Comment · 11 months ago

I am partial to https://huggingface.co/Qwen/Qwen3-Embedding-0.6B nowadays.

Open weights, multilingual, 32k context.