I'm hiring Apache #Kafka and Apache #Flink experts (esp. on the ops side) and engineers experienced with Python for the Kafka & Flink team in @aiven_io. Helsinki 🇫🇮, Berlin 🇩🇪 and also remote in some European 🇪🇺 countries. RT please 😉

RT @yandexcom: Today, Yandex has open-sourced Perforator, a continuous profiling tool that we use to analyze the performance of most servic…

RT @FFmpeg: Interesting how the world has learnt what software optimisation looks like this week #deepseek

I'm working on wrapping some Java code into a native library using GraalVM native image. Do you want a short blog on this?

@naigovan Лол, а сейчас как? ))

RT @andrewlamb1111: The browser based parquet viewer is pretty sweet -- let's you explore the file format, includ…

RT @nrehiew_: .@JeffDean 's full talk at NeurIPS 24 on Machine Learning for Systems and how Google thinks about these things

RT @mitchellh: 👻

RT @durov: Telegram is now profitable 🏆 📈 This year, the number of Telegram Premium subscribers tripled, exceeding 12 million. Our ad reve…

@trueneu Я подумываю взять как-нибудь

@BdKozlovski Yeah, it's there

RT @BdKozlovski: Kafka is about to get a lot cheaper 🔥 @ivan0yu has published KIP-1123: Rack-aware partitioning for the Kafka Producer. 🎅…

@BdKozlovski > [FUTURE KIP] - a Produce to Local Leader KIP, similar to KIP-392, can be introduced to eliminate producer inter-AZ network costs for topics that do not have keys. Here we go:

RT @afedintsev: Lightweight LLMs can be enhanced using Test-Time Compute (TTC). You can take, for example, a 7B LLM and match the performan…

RT @bernhardsson: Running many thousands of GPUs means spending a lot of time knee deep in the CUDA-swamp and other strange places. In the…

The most popular feature requests so far: comment summarization and local LLM support. Will do these next.

RT @dieworkwear: Dislike the term "fatass" here. IMO, it's unnecessary to body shame anyone, regardless of how you feel about them. But I c…

@AnnaTappens А твой манагер?

@AnnaTappens А отказать?