niksa jakovljevic

[niksa jakovljevic @unsigned_mind]

HuggingBench (https://t.co/R87BSpfPen) is designed to assist you in discovering the best setup for serving ML models. 🚀 Here is the blog post explaining our journey and what we are trying to achieve 🛠️📈 https://t.co/7xPIKsFEb7

[niksa jakovljevic @unsigned_mind]

@prijavi_problem ko treba da resi problem deponije na keju pored Beton hale gde prolaze hiljade turista svakodnevno

[clem 🤗 @ClementDelangue]

If AI stays closed-source, proprietary and monopolistic like it is now, it will destroy lots of jobs and just make the richest companies richer and more powerful!

If we open it up thanks to open science and open-source, foster competition and decentralization of value and control, it will create many more jobs and economic value than it destroys.

Let’s go!

[niksa jakovljevic @unsigned_mind]

@MarinaKomad Zvuk aviona koji su mnogi culi je izgleda standardna funkcionalnost LRAD 450XL. Dovoljno da izazove paniku kod ljudi i stampedo

[niksa jakovljevic @unsigned_mind]

Only one more day left to grab this awesome book for for free. Perfect read if you want to get deeper understanding of data structures behind the commonly used databases

[Manos Athanassoulis @manathan1984]

Our book on "Data Structures for Data-Intensive Applications" co-authored with Stratos Idreos (@HarvardDASlab) and @DennisShasha can be downloaded for free from the publisher for the next few days (until Feb 12): https://t.co/0lsOjSC6hy

#FNT #DataStructures #Textbook #Databases

[niksa jakovljevic @unsigned_mind]

As someone who've spent some time benchmarking DBs I can't agree more. Worth reading.

[MotherDuck @motherduck]

Are database benchmarks truly relevant today?
In our latest blog, @jrdntgn explores the limitations of database benchmarks and why they might not be the best tool for selecting a database.
🗞️ https://t.co/2KRx2J11BO

[Andy Pavlo (@andypavlo.bsky.social) @andy_pavlo]

Everything is available to non-CMU students:
* Lectures are on Youtube: https://t.co/qnXILcbP2a
* Slides + Notes on course website.
* Project source code on Github.
* Grading with Gradescope (see FAQ ➡️ https://t.co/aw1jPt7cYl)

Yes, I know my mic got screwed up in Lecture #1.

[niksa jakovljevic @unsigned_mind]

@fredbrancz While ago ClickHouse implemented caching for data stored in shared object storage https://t.co/lBiK0Gd70o

[niksa jakovljevic @unsigned_mind]

How to efficiently 🚀 run BERT model from @huggingface? How do various BERT variants, such as DistilBERT and RoBERTa, stack up in terms of inference throughput 🥊?
⭐ Check out my latest blog post https://t.co/2sK1p8JfOO

[niksa jakovljevic @unsigned_mind]

If you are using Resnet models from @huggingface then the blog post below can help you to save on inference costs

[niksa jakovljevic @unsigned_mind]

I've just published my new blog post that walks you through optimizing Resnet-50 model: 8X inference throughput with only a few commands!
https://t.co/tfhiwOugin

[niksa jakovljevic @unsigned_mind]

I've just published my new blog post that walks you through optimizing Resnet-50 model: 8X inference throughput with only a few commands!
https://t.co/tfhiwOugin

[niksa jakovljevic @unsigned_mind]

Are you using @huggingface models? If so https://t.co/R87BSpfPen might help you find the best model serving setup to increase your inference throughput helping keeping your inference costs low. ⏱️💰

[niksa jakovljevic @unsigned_mind]

Over the last few months, I've been working with my friends to solve the problem of making ML model serving more efficient.💡. It's still early days, but I am excited to introduce you to HuggingBench https://t.co/R87BSpfPen 🌟

[niksa jakovljevic @unsigned_mind]

HuggingBench (https://t.co/R87BSpfPen) is designed to assist you in discovering the best setup for serving ML models. 🚀 Here is the blog post explaining our journey and what we are trying to achieve 🛠️📈 https://t.co/7xPIKsFEb7

[niksa jakovljevic @unsigned_mind]

Details matter especially when building storage systems https://t.co/1NfCS2RtiJ

[Mike Freedman @michaelfreedman]

Team recently did detailed benchmarking of @TimescaleDB and #PostgreSQL across a variety of time-series analytical queries (incl. using PostgreSQL declarative partitionsing).

Can really see the performance benefits of TimescaleDB's columnar compression. 🚀

[niksa jakovljevic @unsigned_mind]

SW engineers as value adders and creative problem solvers, not factory workers. Great read https://t.co/1XU7GYExeT

[zooko🛡🦓🦓🦓 ⓩ @zooko]

Today is a good day for everyone to post this.

[niksa jakovljevic @unsigned_mind]

Great presentation to deepen your knowledge on concurrency

[Felix Geisendörfer @felixge]

📺 Go scheduler: Implementing language with lightweight concurrency (2019)

This presentation by @dvyukov outlining the problems solved by Go's scheduler is 🔥.

Wonderful slides, explanations and examples!

https://t.co/HQ6UU4Mj8F

[niksa jakovljevic @unsigned_mind]

Code review cheat sheet

[Gunnar Morling 🌍 @gunnarmorling]

What to focus on during a code review? Don't waste your time with automatable formalities like code style. Rather spend your review budget on those aspects which will be hard/expensive to change later on. The "Code Review Pyramid" provides some guidance on what to look for.

[Ajay Kulkarni @acoustik]

💥 BIG NEWS!!!

@TimescaleDB just raised a $110 million Series C at a $1+ billion valuation! 💰💰💰

Round led by Tiger Global, with participation from all our existing investors: @benchmark, @NEA, @Redpoint, @iconventures, and @TwoSigmaVC.

https://t.co/lhAPEgb5IV

🐯🦄🚀💥 1/