# Compression Published articles for Compression. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Libreboot 20140811 release DevFeed: [Libreboot 20140811 release]() Original publisher: [Read original article]() Author: Leah Rowe Published: 2026-09-17T04:32:50.666044Z Content type: release Language: en Sources: [News about Libreboot releases and development]() Topics: [libreboot](), [coreboot](), [LVM](), [Compression]() Tags: [article](), [bios](), [canoeboot](), [compression](), [coreboot](), [free-software](), [libre](), [libreboot](), [lvm](), [opensource](), [release](), [uefi](), [xz]() ### AI overview Libreboot 20140811 is the project's fifth beta release. The release notes describe corrections and changes to GRUB modules, documentation, ROM checking guidance, patch organization, bucts files, binary archives, and archive compression. ### Source excerpt Article: Libreboot 20140811 release Web link: https://libreboot.org/news/libreboot20140811.html ## pgBackRest Compression: How Much CPU Is a Smaller Backup Worth? DevFeed: [pgBackRest Compression: How Much CPU Is a Smaller Backup Worth?]() Original publisher: [Read original article]() Author: Agustín Gallego Published: 2026-09-16T21:43:06Z Content type: comparison Language: en Sources: [Blog - Percona]() Topics: [Compression](), [Algorithms](), [PostgreSQL](), [postgresql 18](), [backups](), [Percona]() Tags: [algorithms](), [backup](), [compare](), [compression](), [cpu](), [percona](), [postgresql](), [postgresql-18](), [uncategorized]() ### AI overview This comparison measures pgBackRest compression algorithms and levels on Percona Distribution for PostgreSQL 18.4. It finds that low-level Zstandard offers a favorable balance between CPU use and backup size, with zst(3) near the efficiency curve's shoulder. ### Source excerpt In this blog post, we'll compare pgBackRest's compression algorithms and levels to find where spending more CPU stops buying a meaningfully smaller backup. The short version of the answer, which we'll build up to with real numbers, is that Zstandard at a low level is the sweet spot, and its default (zst(3)) already sits right ... Continued The post pgBackRest Compression: How Much CPU Is a Smaller Backup Worth? appeared first on Percona. ## Understanding W8A8 INT8 LLM quantization: Accuracy and performance results DevFeed: [Understanding W8A8 INT8 LLM quantization: Accuracy and performance results]() Original publisher: [Read original article]() Author: Sana Fayyaz Published: 2026-09-14T13:01:43Z Content type: article Language: en Sources: [Red Hat](), [Red Hat Developer]() Topics: [Large Language Model](), [quantization](), [llama](), [Compression](), [Benchmark](), [dataset](), [Algorithms]() Tags: [ai-inference](), [artificial-intelligence](), [benchmark](), [benchmarks](), [compression](), [evaluation](), [hardware](), [llama](), [llm](), [model](), [models](), [performance](), [quantization](), [reasoning](), [zero-shot]() ### AI overview The article evaluates W8A8 INT8 quantization of a Llama 3.1 8B Instruct model. It describes reducing the model from 14.9 GB to 8.0 GB with SmoothQuant and GPTQ, then compares the base and compressed models on four benchmarks to assess accuracy and performance. ### Source excerpt In Understanding W8A8 INT8 LLM quantization: Half the size, better performance, same accuracy, we compressed a Llama 3.1 8B Instruct model from 14.9 GB to 8.0 GB using 8-bit integer (INT8) W8A8 quantization with SmoothQuant and Generative Pre-trained Transformer Quantization (GPTQ). The post Understanding W8A8 INT8 LLM quantization: Accuracy and performance results appeared first on Red Hat Developer. ## Appwrite 2.1 is now available for self-hosting DevFeed: [Appwrite 2.1 is now available for self-hosting]() Original publisher: [Read original article]() Author: Atharva Deosthale Published: 2026-09-14T00:00:00Z Content type: article Language: en Sources: [Appwrite Blog]() Topics: [Appwrite](), [Amazon S3](), [hosting](), [API](), [API keys](), [Command-line interface](), [SDKs](), [Compression](), [Encryption]() Tags: [api](), [api-documentation](), [aws](), [cli](), [compression](), [encryption](), [hosting](), [products](), [s3](), [self-hosting](), [sign-in]() ### AI overview Appwrite 2.1 is available for self-hosted deployments. It adds the S3-compatible Storage API and AutoGravity image previews, along with TikTok and Kakao sign-in and Appwrite Console fixes. The release uses the existing upgrade command and migration process from Appwrite 2.0. ### Source excerpt Appwrite 2.1 brings the S3 API and AutoGravity to self-hosted instances, adds TikTok and Kakao sign-in, and fixes for Appwrite Console. ## Zstd Improvement For Linux 7.4 To Avoid Redundant Initialization DevFeed: [Zstd Improvement For Linux 7.4 To Avoid Redundant Initialization]() Original publisher: [Read original article]() Author: Michael Larabel Published: 2026-09-13T14:04:23Z Content type: news Language: en Sources: [Phoronix]() Topics: [Compression](), [Linux](), [Benchmark](), [Cryptography]() Tags: [benchmark](), [compression](), [crypto](), [desktop-linux](), [development](), [kernel](), [linux](), [linux-benchmarking](), [linux-hardware-benchmarks](), [linux-hardware-reviews](), [linux-how-to](), [linux-performance](), [linux-server-benchmarks](), [open-source-graphics](), [performance](), [phoronix](), [phoronix-test-suite](), [speed](), [ubuntu-benchmarks](), [ubuntu-hardware]() ### AI overview The article reports Linux 7.4 patches that defer Zstd stream initialization until the first walk iteration, eliminating redundant initialization. Benchmarks show single-digit compression speed improvements and decompression speedups of 13% on bare metal or 35% in a virtual machine. ### Source excerpt In addition to Usama Arif's recent Linux patches for addressing a major inefficiency within the Linux kernel's Zstd compression code, he also has a separate patch series destined for Linux 7.4 to further enhance the Zstd compression/decompression performance by avoiding redundant initialization... ## Cloudflare Tests Cache Transcoding to Reduce Storage Requirements DevFeed: [Cloudflare Tests Cache Transcoding to Reduce Storage Requirements]() Original publisher: [Read original article]() Author: Renato Losio Published: 2026-09-13T10:35:00Z Content type: news Language: en Sources: [InfoQ]() Topics: [Caching](), [Transcodings](), [cloud-infrastructure](), [Pingora]() Tags: [architecture-design](), [cache](), [caching](), [cdn](), [cloud](), [cloudflare](), [cloudflare-cache-transcoding](), [compression](), [cpu](), [data-centers](), [development](), [edge-computing](), [news](), [pingora](), [rust](), [storage]() ### AI overview Cloudflare is testing Cache Transcoding, a prototype that Zstandard-compresses eligible uncompressed text before it is stored in cache. The approach aims to increase effective cache capacity and reduce inter-data-center transfer, with configurable CPU and storage trade-offs. ### Source excerpt Cloudflare recently described a prototype called Cache Transcoding that compresses eligible cache content, mainly uncompressed text such as HTML, JSON, CSS, and JavaScript, using Zstandard before storing it on disk. The hyperscaler estimates that the approach could provide petabytes of additional effective cache capacity, although broader testing is still needed. By Renato Losio ## lld 23 ELF changes DevFeed: [lld 23 ELF changes]() Original publisher: [Read original article]() Published: 2026-09-12T07:00:00Z Content type: release Language: en Sources: [MaskRay]() Topics: [LLVM](), [Git](), [Claude Code]() Tags: [2026](), [compression](), [linker](), [llvm](), [performance](), [release]() ### AI overview This release article summarizes changes in lld/ELF for LLVM 23.1. It reports 141 commits during the development cycle, with substantial performance work including parallelized input-file loading and mark processing, along with linker behavior and compatibility updates. ### Source excerpt LLVM 23.1 has been released. As usual, I maintain lld/ELF and as volunteer work have added some notes to https://github.com/llvm/llvm-project/blob/release/23.x/lld/docs/ReleaseNotes.rst. Like last time, I used Claude Code to summarize git log llvmorg-23-init..origin/release/23.x -- lld/ELF, excluding changes cherry-picked into 22.x (git rev-list llvmorg-23-init..llvmorg-22.1.8 -- lld), and then edited the draft. This was a busy cycle: 141 commits landed in lld/ELF between the branch point (2026-01-13) and 23.1.0-rc1 (2026-07-16), compared with 72 in the 22 cycle. Much of the increase is performance work, which I described in Recent lld/ELF performance improvements. lld 23 is the first release that ships all of it. ## A decade of Rustls DevFeed: [A decade of Rustls]() Original publisher: [Read original article]() Author: jzb Published: 2026-09-09T18:11:54Z Content type: news Language: en Sources: [LWN.net]() Topics: [releases](), [Cryptography](), [Security, Privacy and Abuse Prevention]() Tags: [api](), [blog](), [compression](), [cryptography](), [performance](), [post-quantum](), [releases](), [tls]() ### AI overview A retrospective on ten years of the Rustls TLS-library project, covering its release history, the forthcoming 0.24 and eventual 1.0 releases, and features added in the stable 0.23 line. ### Source excerpt Joe Birr-Pixton has written a blog post reflecting on a decade of the Rustls TLS-library project and looking ahead to the upcoming 0.24 release and an eventual 1.0 release. Rustls began with a first commit on May 2, 2016. Progress was quick: a month later, on June 5, it could interoperate with most sites on the web. The first release, 0.1.0, followed on August 27, 2016 - less than four months after the first commit. [...] From the 0.1.0 release, the project moved through a long series of releases over the following eight years, building out functionality, hardening and refining the API. That sequence of release lines culminated in 0.23, released on February 29, 2024. The 0.23 release line has been a stable one: in the time since, it has seen 43 non-breaking releases. That stability didn't come with stagnation. The 0.23 line delivered a wide range of important features, including a FIPS-certified cryptography option, certificate compression, Encrypted ClientHello, post-quantum cryptography, and performance improvements. ## Architecting for 6 Billion Daily Requests: Inside Wix's Media Platform DevFeed: [Architecting for 6 Billion Daily Requests: Inside Wix's Media Platform]() Original publisher: [Read original article]() Author: Wix Engineering Published: 2026-09-08T08:24:05Z Content type: article Language: en Sources: [Wix Engineering]() Topics: [Caching](), [Go Language](), [Latency](), [Compression](), [data](), [C]() Tags: [c](), [cache](), [caching](), [compression](), [cpu](), [data](), [go](), [latency](), [technical]() ### AI overview Wix describes engineering challenges in its media platform, which processes images, video, and audio at large scale. The supplied text explains how the team used unsafe pointers to reduce Go/C memory-copy overhead for AVIF encoding and a tiered Masters cache to reduce CPU work during image resizing. ### Source excerpt At Wix, "Media" isn't just about storing files. It's about processing streams of information - images, video, and audio - at an immense scale. We host over 300 million websites and serve more than 6 billion media requests every single day. To handle dozens of petabytes of data while keeping costs low and latency minimal, we had to treat media handling as a complex engineering discipline. Below are five specific technical challenges we faced and the architectural solutions we implemented to... ## Understanding W8A8 INT8 LLM quantization: Half the size, better performance, same accuracy DevFeed: [Understanding W8A8 INT8 LLM quantization: Half the size, better performance, same accuracy]() Original publisher: [Read original article]() Author: Sana Fayyaz Published: 2026-09-07T07:01:34Z Content type: article Language: en Sources: [Red Hat Developer]() Topics: [quantization](), [Large Language Model](), [GPU](), [Inference](), [model-deployment](), [Post-training optimization](), [llama](), [LLM Techniques]() Tags: [ai-inference](), [artificial-intelligence](), [compression](), [deployment](), [gpu](), [inference](), [language-models](), [large-language-models](), [llama](), [llm](), [memory](), [performance](), [post-training](), [quantization]() ### AI overview This article explains INT8 W8A8 quantization for Llama 3.1 8B using SmoothQuant and GPTQ. It describes how quantization reduces memory requirements and can improve serving performance while preserving model accuracy, including a reported 46% reduction in model size and planned benchmark testing with vLLM and llm-compressor. ### Source excerpt Large language models are expensive to serve. A model like Llama 3.1 8B in Bfloat16 (BF16) precision occupies roughly 15 GB of GPU memory. In BF16, each of the 8 billion parameters takes 2 bytes to store, which adds up to roughly 15 GB for the weights--and that's not all. The GPU needs memory for the key-value (KV) cache to store context for active requests, alongside intermediate tensor outputs (activations, as we call them) generated during inference. The post Understanding W8A8 INT8 LLM quantization: Half the size, better performance, same accuracy appeared first on Red Hat Developer. ## 5 Embedding Compression Techniques DevFeed: [5 Embedding Compression Techniques]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-09-04T20:51:57Z Content type: tutorial Language: en Sources: [Daily Dose of Data Science]() Topics: [Compression](), [Embeddings](), [quantization](), [Inference]() Tags: [compression](), [embedding](), [inference](), [quantization](), [vector]() ### AI overview A tutorial explaining five embedding compression techniques: PCA, Matryoshka Representation Learning, scalar quantization, binary quantization, and Product Quantization. It describes how they reduce dimensions or per-value precision and how rescoring can improve ranking after compressed retrieval. ### Source excerpt ...explained visually. ## Build a real-time market data app with ClickHouse and Massive DevFeed: [Build a real-time market data app with ClickHouse and Massive]() Original publisher: [Read original article]() Author: Lionel Palacin Published: 2026-09-04T00:00:00Z Content type: tutorial Language: en Sources: [ClickHouse Blog]() Topics: [App](), [data](), [Node.js](), [Back end](), [API keys]() Tags: [analytics](), [api](), [app](), [backend](), [clickhouse](), [compression](), [data](), [demo](), [events](), [how-to](), [latency](), [low-latency](), [node](), [node-js](), [react](), [real-time](), [rest-api](), [storage](), [streams](), [visualization]() ### AI overview A tutorial for building a real-time market-data application that ingests, stores, and queries trade and quote ticks with Massive and ClickHouse, using Node.js for backend work and React for live visualization. ### Source excerpt Learn how to build a real-time financial analytics application with Massive and ClickHouse that scales to thousands of events per second. ## How Turbopack chunks your JavaScript DevFeed: [How Turbopack chunks your JavaScript]() Original publisher: [Read original article]() Author: Sam Poder Published: 2026-09-03T16:00:00Z Content type: article Language: en Sources: [Next.js Blog]() Topics: [modern web development](), [Web Development](), [web applications]() Tags: [cache](), [code](), [compression](), [http](), [javascript](), [next-js]() ### AI overview The article explains how Turbopack groups JavaScript into chunks for Next.js applications. It examines the tradeoff between minimizing downloaded code and minimizing network requests, including the effects on caching and compression. ### Source excerpt Turbopack's chunking speeds up page loads and enables sharing code across pages. We shipped new experimental features to improve chunking in Next.js 16.3. ## How we make AI coding more cost efficient without sacrificing task quality DevFeed: [How we make AI coding more cost efficient without sacrificing task quality]() Original publisher: [Read original article]() Author: Erik Kristensen Published: 2026-09-02T18:00:00Z Content type: article Language: en Sources: [GitHub](), [GitHub Engineering]() Topics: [GitHub Copilot](), [AI-assisted coding](), [GitHub Copilot CLI](), [coding](), [GitHub Copilot app](), [GitHub Copilot code review]() Tags: [agentic-ai](), [agentic-coding](), [ai](), [ai-coding](), [ai-ml](), [architecture-optimization](), [benchmarks](), [compression](), [cost](), [engineering](), [experiments](), [github-copilot](), [github-copilot-cli](), [github-copilot-code-review](), [llms](), [prompt-engineering]() ### AI overview GitHub Copilot's efficiency work focuses on total task cost and duration rather than minimizing tokens in individual tool responses. The article describes evaluating changes with coding benchmarks and controlled experiments, and explains that overly compressed output can cause agents to repeat work. ### Source excerpt Why shorter outputs can cost more, and how GitHub Copilot reduces wasted work across the complete coding task. The post How we make AI coding more cost efficient without sacrificing task quality appeared first on The GitHub Blog. ## How we could save petabytes of cache storage with Zstandard and Pingora DevFeed: [How we could save petabytes of cache storage with Zstandard and Pingora]() Original publisher: [Read original article]() Author: Aashi Patel Published: 2026-09-01T12:59:00Z Content type: article Language: en Sources: [Cloudflare Blog]() Topics: [Caching](), [Pingora](), [cloud-infrastructure](), [Hardware]() Tags: [cache](), [cloudflare](), [compression](), [cpu](), [data-center](), [hardware](), [internship-experience](), [performance](), [pingora](), [prototyping](), [storage](), [testing]() ### AI overview Cloudflare describes a Cache Transcoding prototype that stores eligible cached assets in Zstandard-compressed form. The approach aims to increase effective cache capacity and reduce inter-data-center transfers while adding a small CPU cost during cache fills. ### Source excerpt Could we get more cache space with the same hardware? We prototyped compression inside Cloudflare's cache to find out. ## A Model Portfolio for cost-efficient AI across the software development lifecycle DevFeed: [A Model Portfolio for cost-efficient AI across the software development lifecycle]() Original publisher: [Read original article]() Author: Praveen Sidda Published: 2026-09-01T07:16:01Z Content type: article Language: en Sources: [Data Science at Microsoft]() Topics: [AI Development](), [AI Models](), [Model Routing](), [sdlc](), [Agile](), [Developer experience](), [Compression](), [Requirements](), [Testing](), [Deployment](), [Code review]() Tags: [agentic-sdlc](), [ai](), [ai-cost-optimization](), [ai-models](), [code-review](), [compression](), [deployment](), [github-copilot](), [llm](), [overhead](), [requirements](), [software-development]() ### AI overview The article examines whether routing software development tasks across a portfolio of AI models can reduce costs compared with using one premium model. It reports that lower-cost models handled well-defined tasks, while premium models were reserved for architecture, implementation, and code review; context compression reduced token usage but risked losing important technical details. ### Source excerpt Image generated by AIWhat one controlled experiment taught me about matching model capability to developer work Topic: Can intelligently routing developer tasks across different AI models outperform relying on a single premium model? In this article, I put that question to the test by mapping software development lifecycle (SDLC) stages to a portfolio of AI models and comparing the outcomes. Motivation As AI becomes embedded throughout the AI-Native Development Lifecycle (AIDLC), an evolution of the traditional Software Development Lifecycle (SDLC), its cost is no longer tied to a single prompt. A single developer task can involve multiple model calls, each carrying source files, conversation history, tool definitions, and generated output. Applying the most capable model to every interaction is straightforward, but it also consumes premium model capacity on tasks that less expensive models can often complete just as effectively. This raises an important question for engineering organizations: How can teams reduce the cost of AI-assisted development without compromising quality, reliability, or the developer experience? My first instinct was to reduce token consumption. Context compression appeared to be the most direct path to lowering inference costs by shortening prompts. Although it reduced token usage, it also introduced risk. Important constraints and technical details could be lost, affecting downstream tasks. Source code, stack traces, and active instructions proved to be especially poor candidates for lossy compression. That experience shifted my focus. The objective was not to process fewer tokens, but to complete developer tasks successfully at a lower overall cost. I then experimented with model allocation. Lower-cost models handled well-defined tasks such as requirements synthesis, planning, routine test generation, deployment artifacts, and final summaries, while premium models were reserved for architecture, implementation, and code review. This appro ## Parquet File Write Support, Bloom Filters, Improved Performance: Hardwood 1.1.0.Beta1 Is Out DevFeed: [Parquet File Write Support, Bloom Filters, Improved Performance: Hardwood 1.1.0.Beta1 Is Out]() Original publisher: [Read original article]() Published: 2026-08-31T19:36:00Z Content type: release Language: en Sources: [Gunnar Morling]() Topics: [parquet](), [Library](), [Parser](), [Command-line interface](), [Compression]() Tags: [apache-parquet](), [api](), [cli](), [compression](), [library](), [parquet](), [performance](), [release]() ### AI overview The first beta of Hardwood 1.1 introduces initial Parquet file-writing support through record-based and batch-oriented APIs. The release also adds Bloom filters, dictionary-based row-group pruning, performance improvements, and CLI enhancements. ### Source excerpt Table of Contents Write Support Query Evaluation: Bloom Filters and Dictionary-Based Row-Group Pruning Performance Improvements Hardwood CLI Closing Thoughts "When is write support gonna land in Hardwood?" That's probably the most common question I got over the last few months. As of today, I am very happy to share that the answer has changed from "It's coming soon" to "A first cut is there, give it a try" -- the first Beta of Hardwood 1.1 is out! This is a major milestone for the project, marking the first step in evolving Hardwood from being solely a Parquet parser to a complete library for this widely used columnar file format. But there's more. This release also comes with significant enhancements to the query layer (Bloom filters, dictionary-based row-group pruning), many performance improvements such as a fast path for effectively fixed-length list columns, an even snappier CLI, and much more. Let's dig into some of the new features and changes! ## Paperless-ngx 3.1.0 Adds AI Workflow Actions and Document Versioning DevFeed: [Paperless-ngx 3.1.0 Adds AI Workflow Actions and Document Versioning]() Original publisher: [Read original article]() Author: Christian Rakoot Published: 2026-08-31T06:39:07Z Content type: news Language: en Sources: [Self Host Lab]() Topics: [Artificial Intelligence](), [OpenID connect (OIDC)](), [Compression](), [Open Source](), [Authorization]() Tags: [ai](), [bug](), [changelog](), [compression](), [identity](), [news](), [news-personal-cloud](), [ocr](), [open-source](), [paperless-ngx](), [personal-cloud](), [release](), [self-hosted](), [updates](), [workflow]() ### AI overview Paperless-ngx 3.1.0 adds automatic AI-based workflow classification, per-document remote OCR selection, OIDC group synchronization, document versioning, configurable ZIP compression, and smaller fixes. ### Source excerpt Paperless-ngx 3.1.0 landed on August 27, 2026, adding a workflow action that applies AI-generated tag and correspondent suggestions automatically, per-document selective remote OCR, OIDC group sync mapping identity-provider groups to superuser and staff roles, a new versioning system for merging documents into successive versions, configurable ZIP export compression, and numerous smaller UI bug fixes sitewide. ## IDEA Prune: An Integrated Enlarge-and-Prune Pipeline in Generative Language Model Pretraining DevFeed: [IDEA Prune: An Integrated Enlarge-and-Prune Pipeline in Generative Language Model Pretraining]() Original publisher: [Read original article]() Published: 2026-08-26T00:00:00Z Content type: article Language: en Sources: [Apple Machine Learning Research]() Topics: [Language models](), [compression and generalization](), [Training AI Models](), [Inference Performance]() Tags: [compression](), [generative](), [inference](), [language-models](), [large-language-models](), [model](), [training]() ### AI overview This paper presents IDEA Prune, an integrated enlarge-and-prune pipeline for generative language model pretraining. It combines enlarged-model training, iterative structured pruning, and recovery under one cosine annealing learning-rate schedule, with experiments compressing 2.8B models to 1.3B. ### Source excerpt Recent advancements in large language models have intensified the need for efficient and deployable models within limited inference budgets. Structured pruning pipelines have shown promise in token efficiency compared to training target-size models from scratch. In this paper, we advocate incorporating enlarged model pretraining, which is often ignored in previous works, into pruning. We study the enlarge-and-prune pipeline as an integrated system to address two critical questions: whether it is worth pretraining an enlarged model even when the model is never deployed, and how to optimize the... ## Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original DevFeed: [Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original]() Original publisher: [Read original article]() Author: Antonio Tiene; Iker García-Ferrero; Ali Hashemi; Bakbergen Ryskulov Published: 2026-08-25T11:39:24Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [AI Chat]() Tags: [architecture](), [benchmarks](), [blog](), [compression](), [fine-tuning](), [gpt](), [gpt-oss](), [hugging-face](), [llms](), [model](), [post-training](), [quantization](), [rlhf]() ### AI overview The article presents Quantization-Aware Healing (QAH), a method for recovering structurally compressed and 4-bit-quantized LLMs. It contrasts QAH with quantization-aware training and distillation, arguing that the latter can be limited when no independently trained full-precision version of the compressed architecture exists. ### Source excerpt A Blog post by Multiverse Computing on Hugging Face ## Gisting: Compressing LLM Agent context to ↑ throughput and ↓ cost DevFeed: [Gisting: Compressing LLM Agent context to ↑ throughput and ↓ cost]() Original publisher: [Read original article]() Author: Cody Mazza-Anthony Published: 2026-08-19T14:32:58Z Content type: article Language: en Sources: [Shopify Engineering](), [Shopify Engineering - Shopify Engineering]() Topics: [Compression](), [Large Language Model](), [Embeddings](), [Latency](), [Inference](), [Inference Performance](), [Low-Latency Inference](), [Post-training optimization](), [GraphQL](), [model-deployment]() Tags: [compression](), [embedding](), [inference](), [latency](), [llm](), [model](), [tokens]() ### AI overview Gisting compresses an LLM agent's system prompt into learned gist tokens, preserving prediction quality while reducing inference latency, increasing throughput, and lowering GPU requirements. ### Source excerpt Gisting compresses context into a set of learned tokens, preserving its quality while making the model faster and cheaper. ## Scale pgvector with binary quantization on Amazon Aurora PostgreSQL DevFeed: [Scale pgvector with binary quantization on Amazon Aurora PostgreSQL]() Original publisher: [Read original article]() Author: Steve Dille Published: 2026-08-18T16:37:22Z Content type: tutorial Language: en Sources: [AWS Database Blog]() Topics: [Amazon Aurora](), [PostgreSQL](), [quantization](), [AI search](), [Compression](), [Embeddings](), [Cache](), [Latency](), [datasets](), [configuration](), [postgresql clusters](), [Database]() Tags: [advanced-300](), [ai](), [amazon-aurora](), [cache](), [compression](), [datasets](), [embeddings](), [latency](), [postgresql](), [postgresql-compatible](), [quantization](), [rds-for-postgresql](), [search](), [technical-how-to](), [validation](), [vector]() ### AI overview This practical guide explains how to use binary quantization with reranking in pgvector to scale HNSW vector search on Amazon Aurora PostgreSQL. It covers index-size reduction, performance and recall tradeoffs, sizing, validation, and suitable operating conditions for datasets ranging from 5 million to 100 million vectors. ### Source excerpt Learn how to use binary quantization with reranking (HNSW+BQ) in pgvector to scale vector search to hundreds of millions or billions of vectors on Amazon Aurora PostgreSQL, with practical guidance on index sizing, recall validation, and the scenarios where the approach works best. ## MiniDXNN v0.4.0: Interactive neural texture compression on DirectX 12 DevFeed: [MiniDXNN v0.4.0: Interactive neural texture compression on DirectX 12]() Original publisher: [Read original article]() Author: Takahiro Harada; Sho Ikeda Published: 2026-08-13T14:30:00Z Content type: release Language: en Sources: [AMD GPUOpen]() Topics: [Compression](), [GPU](), [Inference](), [mlp](), [Machine learning](), [GUI](), [shaders](), [Open Source]() Tags: [agility-sdk](), [announcement](), [compression](), [directx](), [driver](), [getting-started](), [gpu](), [gpu-open-sdks](), [gpu-open-tools](), [gpuopen-sdks](), [gpuopen-tools](), [graphics-apis](), [gui](), [inference](), [maths](), [memory](), [microsoft](), [microsoft-agility-sdk](), [microsoft-directx](), [ml](), [mlp](), [neural](), [open-source](), [product-release](), [quick-start](), [real-time](), [shaders](), [technical-article](), [technical-articles](), [tools]() ### AI overview MiniDXNN v0.4.0 is an open-source library for GPU-accelerated MLP inference and training on DirectX 12. The release adds D3D12 Linear Algebra support, input encoding for neural texture compression, and a real-time GUI application for training and visualizing texture representations. ### Source excerpt MiniDXNN v0.4.0 introduces D3D12 Linear Algebra (SM 6.10) support, input encodings and neural texture compression, plus a real-time GUI app that trains and visualizes GPU-accelerated MLPs on DirectX® 12. ## Inside Appwrite's new build cache: 4x faster dependency installs DevFeed: [Inside Appwrite's new build cache: 4x faster dependency installs]() Original publisher: [Read original article]() Author: Torsten Dittmann Published: 2026-08-13T00:00:00Z Content type: article Language: en Sources: [Appwrite Blog]() Topics: [Appwrite](), [Caching](), [Cache](), [Deployment](), [Next.js](), [Package manager](), [Compression](), [cloud-infrastructure]() Tags: [cache](), [compression](), [dependencies](), [deployment](), [engineering](), [filesystem](), [next-js](), [object-storage](), [pnpm](), [production]() ### AI overview Appwrite's build network caches dependencies between builds for sites and functions. The cache is restored before installation and saved after successful builds, with snapshots isolated per resource. The article explains how Appwrite uses SquashFS images to efficiently store and unpack package-manager data, reporting faster installs for example Next.js applications. ### Source excerpt A deep dive into how Appwrite now caches your dependencies between builds, and what it means for your deployment times. [Next page]()