Viewing profile — rrevi
rrevi
HN member- Joined
- Thu, Jan 06, 2022, 7:00 PM UTC
- HN karma
- 14
- Public activity
- 18 items
- HN profile
- View on Hacker News ↗
About rrevi
Recent public activity
-
comment
Comment #48495558
I have been using MTPLX (replaced oMLX for me) on my M5 Pro with 64GB with Qwen3.6 27B Optimized Quality (getting about 16-19 generated tps, which is exactly double what I saw befo…
- story
-
comment
Comment #48468378
related https://x.com/cohere/status/2064378058329526556
-
comment
Comment #47965778
The device nomenclature alone is worth the read! (otherwise an impressive feat to see)
- story
-
comment
Comment #41968986
Which now begs the question, sqlite3_rsync vs Litestream[0]? [0] https://litestream.io/
-
comment
Comment #41968732
And made it to the news section of the SQLite site on Oct. 21st 2024: https://sqlite.org/news.html
- story
-
comment
Comment #34114357
More on bail bonds: https://youtu.be/IS5mwymTIJU And more on bail reform: https://youtu.be/xQLqIWbc9VM
-
comment
Comment #33225063
See here https://crystal-lang.org/used_in_prod/
- story
- story
-
comment
Comment #32087110
Thanks for sharing compumike! Very cool!! If you don’t mind me asking, why did you choose the Crystal programming language for this project?
-
comment
Comment #32086959
“Rendered by the Crystal programming language in 739 µs.” Very nice!
-
comment
Comment #32001931
Thanks! I'm sure this type of benchmark (bubble sort) has been done many times over in the past. But yes, it'd be interesting to see it across ruby versions, ruby implementations, …
- story
- story
- story