https://www.unum.cloud/blog/ Deep dives on USearch, UStore, UForm and the libraries beneath them: benchmarks, kernels and storage engines en https://www.unum.cloud/blog/development-practices https://www.unum.cloud/blog/development-practices Mon, 09 Nov 2026 00:00:00 GMT A decade in, AI agents made writing code cheap and keeping it coherent expensive. How that changed our Git branches and releases, moved eight repositories into lockstep, turned pre-commit hooks into design guardrails, made model checking routine, and what we still have not figured out https://www.unum.cloud/blog/float8 https://www.unum.cloud/blog/float8 Mon, 20 Apr 2026 00:00:00 GMT GPUs moved to FP8. CPUs didn't. 200'000 lines of SIMD kernels later, USearch bridges both worlds — native Float8 Vector Search and KV Caching for the upcoming Arm-based NVIDIA Vera racks, Intel Xeons, open-source RISC-V chips, IBM Mainframes, Chinese LoongArch, and even WebAssembly in the browser — for higher throughput at 99% recall and half the memory cost https://www.unum.cloud/blog/scaling-vector-search-with-intel https://www.unum.cloud/blog/scaling-vector-search-with-intel Tue, 07 Nov 2023 00:00:00 GMT Scaling Retrieval Augmented Generation with the USearch vector search engine on Intel Sapphire Rapids CPUs on Gcore, outperforming Meta's FAISS library by 10x - 100x on a scale of 100M to 1B vectors. https://www.unum.cloud/blog/uform-graphcore https://www.unum.cloud/blog/uform-graphcore Thu, 17 Aug 2023 00:00:00 GMT Releasing UForm v2 with support for 21 languages, delivering state-of-the-art efficiency in AI-based text-to-image search and multimodal embeddings. https://www.unum.cloud/blog/intel-gcore-unum https://www.unum.cloud/blog/intel-gcore-unum Thu, 08 Jun 2023 00:00:00 GMT Partnering with Gcore and Intel to deploy the world most efficient data-processing infrastructure at the edge, powered by Unum assembly-optimized engines. https://www.unum.cloud/blog/efficient-multimodality https://www.unum.cloud/blog/efficient-multimodality Mon, 20 Feb 2023 00:00:00 GMT Demonstrating how to train state-of-the-art Vision-Language transformers for semantic search using 100x less data and compute than OpenAI CLIP. https://www.unum.cloud/blog/pandas https://www.unum.cloud/blog/pandas Tue, 20 Sep 2022 00:00:00 GMT Evaluating in-memory tabular processing frameworks including CuDF, Modin, Arrow, and Spark on billion-row taxi ride datasets to find the fastest Pandas alternative. https://www.unum.cloud/blog/ucsb-10tb https://www.unum.cloud/blog/ucsb-10tb Tue, 13 Sep 2022 00:00:00 GMT Pushing the limits of UDisk and RocksDB on massive 10TB datasets with 64 threads and 1TB of RAM, achieving up to 7x performance gains in almost every workload. https://www.unum.cloud/blog/ucsb https://www.unum.cloud/blog/ucsb Tue, 22 Mar 2022 00:00:00 GMT Introducing the Unum Cloud Serving Benchmark (UCSB), a modernized and extended version of YCSB designed to rigorously evaluate the performance of next-generation storage engines. https://www.unum.cloud/blog/cupy https://www.unum.cloud/blog/cupy Wed, 26 Jan 2022 00:00:00 GMT Accelerating NumPy workflows by 50x using CuPy on Nvidia RTX 3090, benchmarking BLAS operations against CPU-based implementations on AMD Threadripper. https://www.unum.cloud/blog/cpu-vs-gpu https://www.unum.cloud/blog/cpu-vs-gpu Tue, 25 Jan 2022 00:00:00 GMT Comparing the number-crunching capabilities of AMD Threadripper PRO 3995WX and Nvidia RTX 3090 across matrix multiplication, convolution, and other compute-intensive tasks. https://www.unum.cloud/blog/dbms-startups https://www.unum.cloud/blog/dbms-startups Fri, 31 Dec 2021 00:00:00 GMT A retrospective on the database industry in 2021, analyzing the technical architecture, funding rounds, and market promises of the hottest new database startups. https://www.unum.cloud/blog/ycsb-udisk https://www.unum.cloud/blog/ycsb-udisk Thu, 25 Nov 2021 00:00:00 GMT Benchmarking UDisk against RocksDB, LevelDB, and WiredTiger on 1TB datasets, demonstrating superior performance in read-heavy and write-heavy workloads. https://www.unum.cloud/blog/ycsb-keyval https://www.unum.cloud/blog/ycsb-keyval Wed, 27 Oct 2021 00:00:00 GMT A deep dive into the Yahoo Cloud Serving Benchmark to evaluate NoSQL database performance, identifying the strengths and weaknesses of RocksDB, LevelDB, and WiredTiger. https://www.unum.cloud/blog/bottlenecks https://www.unum.cloud/blog/bottlenecks Tue, 05 Jan 2021 00:00:00 GMT Exploring the limits of modern hardware through Assembly optimizations, CUDA kernels, and algorithmic improvements to eliminate IO and compute bottlenecks in database engines. https://www.unum.cloud/blog/texts https://www.unum.cloud/blog/texts Sun, 03 Jan 2021 00:00:00 GMT Comparing indexing performance of ElasticSearch, MongoDB, and UDisk on a 20GB text dataset, revealing the massive overhead of Java-based search engines. https://www.unum.cloud/blog/why-build-dbms https://www.unum.cloud/blog/why-build-dbms Sat, 02 Jan 2021 00:00:00 GMT Analyzing the widening gap between modern NVMe SSD throughput and legacy database software performance, and why we decided to build a new storage engine from scratch. https://www.unum.cloud/blog/graphs https://www.unum.cloud/blog/graphs Thu, 12 Nov 2020 00:00:00 GMT Benchmarking graph traversal performance on persistent storage against NetworkX, evaluating random access patterns on Patent Citations, Gene Regulatory Networks, and Human Brain connectomes.