Loading…
Topic
160 posts about Deployment. Every summary links to the original.
See the idea
A/B testing trades traffic, time, and exposure risk for evidence. This explainer maps the benefit of a controlled comparison, the real cost of running one, and the condition that decides when measuring beats shipping on judgment.
Bun packs a runtime, package manager, bundler, and test runner into one binary. Here is how those four parts fit together and where the seams still show.
CloudFormation is a declarative reconciler: you describe the target state in a template, and it provisions, updates, and reports on the stack that results. Here is the loop.
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
Newest first
Cursor introduces builds for Cloud Agents, continuously prepared copies of development environments that replace just-in-time machine boot, repository cloning, dependency installation, and install-script execution. Builds run by default every hour; successful builds become the starting point for future agents, which fork warm live machines rather than restoring environments from disk. The post reports 10x faster internal environment boot times and 3x faster time to first token, while customers cite quick starts and uninterrupted automated runs when builds fail. If a dependency bump or Docker build breaks installation, the failed build stays inactive and sessions continue from the last successful version while debugging proceeds. The Cloud Agents dashboard exposes build status, logs, captured commit SHAs, and run-to-build links, while a git-state threshold and Cursor Cloud MCP support oversight; setup requires moving preparable work into install and reserving fresh services for start.
Alibaba’s Qwen3.8-2.4T-A95B (Qwen3.8-Max) is an open-weight 2.4T-parameter model with 95B activated per token, designed for reasoning and agentic workloads. Its fine-grained mixture-of-experts architecture combines full and linear attention, supporting context of up to one million tokens and output lengths up to 128K while using bounded recurrent state in linear-attention layers. NVIDIA describes multinode serving on the 72-GPU GB300 NVL72, where a 130 TB/s NVLink domain supports expert communication; in FP8, the model reportedly exceeds 4K tokens per second per GPU and 350 tokens per second per user without additional tuning. Developers can control reasoning depth with low, high, or xhigh modes, choose SGLang, vLLM, NVIDIA Dynamo, or NIM for serving, and use NeMo AutoModel for full SFT or LoRA post-training.
NVIDIA Nemotron 3.5 Lightning is an open 30B mixture-of-experts model with 3B active parameters, designed for the high-volume execution layer of long-running autonomous agents. The post positions it alongside frontier reasoning models: larger systems handle planning and orchestration, while Lightning handles tool calls, result validation, subagent delegation, and other routine work. Its design combines harness-optimized training, multi-token prediction for speculative decoding, DFlash and DSpark draft models, and NVFP4 quantization alongside BF16. The model is customizable through LoRA or full SFT, reinforcement learning, and environment-based evaluations, with weights, training data, and recipes released under OpenMDW-1.1. The post reports up to 4x the output speed of similar-sized models, 86% accuracy on PinchBench, and completion of 10,000 tasks 30% faster than Qwen3.6 35B at similar accuracy, while NeMo Switchyard routes work among models.
NVIDIA Magpie Multilingual TTS is a 364M-parameter open-weights model for multilingual voice applications, supporting 12 languages, including newly added Modern Standard Arabic, Korean, and Brazilian Portuguese. It is positioned for cascaded voice-agent architectures in which ASR, TTS, and LLM components are independently deployed, tuned, and scaled on controlled infrastructure. Frame stacking predicts two audio frames per decoding step, while a local transformer models dependencies between simultaneously generated codebook tokens; NVIDIA reports 32–79 ms single-stream TTFA across its listed GPUs. Compared with the previous release, French and Spanish CER improved to 1.54% and 0.60%, while SSIM reached 0.747 and 0.793; German SSIM also increased to 0.742. The Hugging Face checkpoint supports research and fine-tuning, while NVIDIA NIM provides optimized production serving and NeMo supports customization.
Meta has released Muse Glimmer, a 30B open-weight dense model with a 120K+ context window aimed at local agentic AI workflows. The model uses a dense architecture that activates every parameter per token, avoiding routing overhead and targeting reliable instruction following, long-context coherence, and predictable latency for multi-step agent tasks. On NVIDIA Blackwell Ultra hardware, Muse Glimmer reports over 20K tokens/sec/GPU at BF16/NVF4 precision, with the full model fitting in a single GPU's VRAM. Deployment options span NVIDIA GeForce RTX 5090, DGX Spark, DGX Station, and Jetson edge devices, supported by vLLM, SGLang, and NVIDIA NIM containers. Fine-tuning is available through NVIDIA NeMo AutoModel for SFT and LoRA, with NeMo RL for reinforcement learning, and the NemoClaw harness enables long-running assistants in a sandboxed environment.
Meta’s Muse Glimmer is a 30B-parameter multimodal model released under the Apache 2.0 license for local, agentic applications including coding, document analysis, and personal assistants. Its dense architecture combines a 2B ViT-style perception encoder with a 28B text decoder, while an optional DFlash speculative-decoding drafter targets faster generation for structured content. The decoder uses alternating sliding-window and full-attention layers, grouped-query attention, and query-key normalization with extra query scaling. Day-zero support is available in Transformers, llama.cpp, vLLM, Inference Endpoints, and other libraries, with examples for text, images, videos, deployment, and agent workflows. Published benchmarks show varied results: Muse Glimmer leads on MCP Atlas and SWE-Bench Pro, while Qwen3.6 leads on OSWorld-Verified and SWE-Bench Verified.
NVIDIA Ising Calibration is an open-source vision language model designed to interpret quantum processor diagnostic outputs and recommend tuning steps. The newly released Ising Calibration 1.5 features a 31-billion-parameter architecture that is 11.4% smaller at BF16 precision than its predecessor. Trained on multi-modality partner data including superconducting qubits, quantum dots, ions, neutral atoms, and electrons on Helium, the model supports both zero-shot reasoning and in-context learning. Evaluated on the QCalEval benchmark, it scores 10% higher on average than comparable open models in zero-shot tasks and improves in-context learning performance by over 86% relative to the prior release. In addition to BF16 weights, the model offers an NVFP4 quantization option suitable for deployment on single consumer GPUs or NVIDIA DGX Spark hardware.
The update presents a production inference platform for open-weight, licensed closed-weight, and fine-tuned models, aimed at giving teams control over performance, cost, quality, and functionality without building an inference stack from scratch. It supports uploading weights or adapters from Hugging Face, S3, or local machines, uses tested deployment profiles for hardware, quantization, tensor parallelism, speculative decoding, and serving engine choices, and lets operators tune placement and autoscaling signals. Endpoints can keep a stable interface while multiple deployments receive traffic through canary, blue-green, rolling, A/B, or shadow testing, with threshold-based automatic rollback. The rebuilt caching and distribution layer proactively warms shared weights; internal testing reports roughly 4× faster warm starts across several frontier models, while a closed beta adds full-weight and LoRA reinforcement learning and supervised fine-tuning with deployable checkpoints.
Thumbtack manages marketplace pricing by updating hundreds of thousands of bid settings stored in DynamoDB across service offerings. Previously executed through individual custom Go scripts, these pricing rollouts lacked automated runtime state tracking, dynamic database throughput pacing, and durable records for reliable rollbacks. To eliminate manual operational risk, engineering introduced a shared deployment-like engine that accepts declarative target states and executes pure Go transformation functions without direct I/O. The engine enforces idempotency, conducts dry runs with validation reports to S3, coordinates atomic DynamoDB updates with audit logging, and dynamically manages write capacity. This platform standardizes pricing updates into reviewable, resumable, and reversible operations that safely skip already written rows and check for production drift during rollbacks.
Managing Infrastructure as Code across distributed repositories presents significant security and operational challenges. Pinterest developed the Resource Provisioner Pipeline (RPP), a proprietary Terraform execution engine, to securely deploy and manage AWS infrastructure across hundreds of workspaces. The pipeline utilizes centralized GitHub composite actions triggered by pull request events and enforces dual human approvals. To maintain least privilege, RPP uses GitHub OpenID Connect authentication to assume a central identity before validating repository paths and down-scoping to specific team execution roles. Automated checks include backend state validation, linting, plan generation, Semgrep static analysis, and optional LocalStack testing before deliberate comment-driven deployments execute.
AWS CloudFormation custom resources extend template provisioning capabilities but lack built-in multi-Region coordination, risking duplicate executions and unhandled failures during regional outages. To solve this limitation, an active-active architecture leverages Amazon Simple Notification Service topics to fan out lifecycle events across primary and secondary infrastructure Regions. The primary Region processes events immediately, whereas the secondary Region processes incoming messages after a deliberate delay implemented via Amazon Simple Queue Service. Coordination relies on Amazon DynamoDB Global Tables with conditional writes to manage distributed locking and enforce idempotency. When failures occur in the primary Region, Amazon CloudWatch alarms signal Amazon Application Recovery Controller to automate failover without manual intervention.
Industrial edge environments often face significant unplanned downtime yet lack reliable cloud connectivity to run large-scale artificial intelligence models. To address this limitation, an offline-first reference architecture shifts generative inference to edge devices while leveraging cloud services for preparation and lifecycle management. The workflow uses Amazon Bedrock with Amazon Nova Pro to create labeled dataset pairs, Amazon SageMaker AI Pipelines to fine-tune a compact model, and AWS IoT Greengrass to orchestrate edge deployments. Local execution relies on Ollama, Strands Agents, and a CPU-based ChromaDB retrieval pipeline that consumes zero GPU VRAM. In evaluations across three foundation model judges, the fine-tuned gpt-oss-20b model combined with retrieval-augmented generation consistently outperformed the base model configuration across accuracy, completeness, and relevance metrics.
Devin, an AI software engineer by Cognition, plans, writes, tests, and ships code semi-autonomously. Cognition now extends Devin with Outposts, moving execution into user-controlled environments while reasoning stays in Cognition’s cloud. Modal is a launch partner with modal-devin, an open-source integration running Outpost sessions in Modal Sandboxes with pre-built custom images, fast cold-starts, snapshotting, and cost-efficient bursting. For example, a task that requires a GPU fails immediately in the default sandbox but succeeds on a Modal-backed Outpost that spins up a GPU on demand and scales to zero when done. One command, uvx modal-devin init, sets up secure infrastructure with a scheduler and worker functions, and each team can have its own outpost with separate credentials.
The guide explains how to add a Heroku staging environment so changes are tested in a near-identical, isolated replica before production. It uses a pipeline with production and staging apps, disables production automatic deployments, connects staging to GitHub, and enables automatic builds, with Review Apps offered for pull requests. The setup applies Twelve-Factor practices by separating config vars and databases, recommending migrations into a fresh Postgres database or warning that pg:copy overwrites staging data and can create compliance risks. After validation, slug promotion sends the exact compiled staging asset to production without recompiling, while numbered releases support rollback; database changes must still be reversed separately.
Unified Logs enters open beta, bringing events from the API gateway, Postgres, Auth, Storage, PostgREST, Realtime, and connection poolers into one searchable dashboard view. Before this, debugging a single request required separate log pages, service-specific filters, and manual correlation across tabs, which slowed investigation and risked losing context. Users can filter by log type, level, status, method, or pathname, search event messages, share URL-based filter states, stream new events live, and zoom into timeline ranges colored by log level. Clicking a row opens a detail panel that presents network timing, gateway, database query, and Auth blocks alongside raw JSON, while Log Drains forward events to external destinations. The feature is rolling out to all projects during open beta, with the classic Logs Explorer still available and feedback requested.
Thinking Machines Lab has released Inkling and the smaller Inkling-Small family as open multimodal models that accept image, text, and audio inputs. Inkling is described as a roughly 1T-parameter decoder-only Mixture-of-Experts model, with 975B total and 41B active parameters, a 1M-token context window, and training on 45 trillion multimodal tokens. Its architecture combines relative attention, alternating global and sliding-window attention, short convolution, shared experts, hierarchical image patchification, and discretized mel-spectrogram audio processing. The release includes BF16 and NVFP4 checkpoints, speculative MTP layers, day-zero support in Transformers, SGLang, vLLM, and llama.cpp, plus deployment configurations and interactive voice and image demos. Reported benchmarks show Inkling and Inkling-Small achieving strong but varied results across reasoning, coding, vision, audio, factuality, chat, and safety evaluations.
Slack developed Shipyard to modernize its EC2 infrastructure by replacing continuously updated, mutable instances with immutable deployable artifacts. The platform adopts a layered image architecture starting with a standardized base image called slack-zero, which is built using AWS Image Builder and consumed by downstream service-specific machine images. Rather than running periodic Chef jobs in the background, configuration management is restricted to image baking and initial instance provisioning phases. Fleet management is handled through the Peekaboo inventory system, metric-driven progressive rollouts via Gondola, and automated instance rotation managed by a lifecycle component known as the Reaper. Developers validate cookbook updates prior to merging using Ship Quick, which provisions real infrastructure across dedicated worker fleets to verify provisioning workflows.
Adapting vision reasoning models for specialized physical AI video tasks often demands days of manual container configuration, training script authoring, and hyperparameter tuning. NVIDIA Cosmos 3 Nano, an omnimodal mixture-of-transformers model, pairs an autoregressive Reasoner tower with an iterative diffusion Generator tower for video question answering. By integrating NVIDIA TAO agent skills with a coding agent like Codex, developers can automate data patching, evaluation, and Low-Rank Adaptation (LoRA) post-training. In experiments using the Woven Traffic Safety dataset, LoRA fine-tuning boosted zero-shot baseline accuracy from 54.41% to 87.14% while using approximately seven times fewer GPU hours than full-parameter supervised fine-tuning. Combining this agent workflow with TAO AutoML further elevated model accuracy to 93.35% before automated deployment via NVIDIA NIM.
ClickHouse is now available as Docker Hardened Images (DHI), stripped-down builds for the ClickHouse server, ClickHouse Keeper, Kubernetes Operator and Helm chart, and metrics exporter. The standard image’s Ubuntu 22.04 base includes unused packages such as Perl, wget, and apt, whose known CVEs can block enterprise deployments even though ClickHouse does not use them. DHI replaces that base with a minimal image that has no package manager or network tools, runs as non-root, provides SLSA Level 3 provenance, and is maintained for CVE patching; Docker Scout reported 0 medium and 14 low findings for DHI, versus 8 medium and 11 low across 111 packages in the standard image. Migration preserves volumes and configuration, while development tooling remains available through a dev variant or temporary docker debug attachment.
Lyft developed Aria, an AI-powered assistant allowing approved employees to query ride analytics via natural language through a backend with LangGraph orchestration and SQL generation. However, Aria's user interface was limited to a Streamlit prototype that lacked standard service framework integration, Lyft authentication, and multi-user scalability. To resolve these limitations, a new engineer built a production-grade web client from scratch using Lyft's internal Node.js framework and Next.js as a three-week onboarding assignment. The implementation involved configuring Envoy routing, resolving authentication plugin incompatibilities, debugging service connectivity with Grafana, and managing interface state with an XState state machine. Aria was successfully hardened and launched into production, expanding natural language analytics access across the company.
The best engineering reads, once a week.
