Perforator is a cluster-wide continuous profiling tool designed for large data centers

Towards a New File Format

Code for the paper: "No Zero-Shot Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance" [NeurIPS'24]

Solution of the telegram ML competition 2023

The PolymurHash universal hash function.

Hash collisions and exploitations

YTsaurus is a scalable and fault-tolerant open-source big data platform.

Animation engine for explanatory math videos

🦔 Fast, lightweight & schema-less search backend. An alternative to Elasticsearch that runs on a few MBs of RAM.

Port of OpenAI's Whisper model in C/C++

Compressed Log Processor (CLP) is a free log management tool capable of compressing logs and searching the compressed logs without decompression.

Dictionary-based compression for inverted indexes.

Sioyek is a PDF viewer with a focus on textbooks and research papers

Master programming by recreating your favorite technologies from scratch.

Unicode routines (UTF8, UTF16, UTF32) and Base64: billions of characters per second using SSE2, AVX2, NEON, AVX-512, RISC-V Vector Extension, LoongArch64, POWER. Part of Node.js, WebKit/Safari, Lad…

Configure keys, macros, and lighting on GK6X keyboards (GK64, GK84, GK61, etc)

Benchmarking suite for Google workloads

Pretrained language model with 100B parameters

A small study in hardware accelerated AoS reversal

Frame profiler

YDB is an open source Distributed SQL Database that combines high availability and scalability with strong consistency and ACID transactions

Hydra adds resilience and high availability to remote memory solutions.

SanRazor is a sanitizer check reduction tool aiming to incur little overhead while retaining all important sanitizer checks.

Expressive Vector Engine - SIMD in C++ Goes Brrrr

Concurrent Deferred Reference Counting

Fast Approximate Membership Filters (C++)

The design and algorithms used in Cacheus are described in this USENIX FAST'21 paper and talk video: https://www.usenix.org/conference/fast21/presentation/rodriguez