Vercel CDN Cache Tags vs Path Purging: When Tag Invalidation Wins
Vercel's tag-based cache invalidation shifts cost from each purge call to per-response edge metadata, forcing teams to design a low-cardinality tag taxonomy up front.
The archive · Page 5 of 7
Infrastructure & Runtime
The serving stack, network fabric, and cloud-account substrate beneath production AI, where every throughput claim collides with rebuild windows, egress invoices, and control-plane risk.
The archive
97–120 of 145 articles · Newest first
Prisma Joins the Vercel Marketplace: The ORM Becomes the Database Vendor
Prisma Postgres now bills through Vercel Marketplace, turning the ORM company into your database vendor. Transactional pool limits constrain serverless workloads.
OpenAI on AWS Bedrock: Routing Math to Run Before You Move Traffic
OpenAI on AWS Bedrock is unconfirmed, but a loosened Microsoft deal would let AWS shops draw down committed spend rather than pay cross-cloud egress for GPT-class models.
Vercel's Function Observability: What Native Metrics Replace and What They Don't
Vercel Observability surfaces per-function cost and error metrics natively, retiring basic Datadog for cost attribution, but cannot trace cross-service latency chains.
AWS Databases on the Vercel Marketplace: The Cross-Cloud Latency Tax
Vercel's AWS Databases marketplace streamlines IAM and billing but leaves cross-region latency and pooling on the buyer. The 64ms benchmark holds only on greenfield accounts.
Turso on Vercel is a remote database integration, not embedded SQLite
Turso on Vercel is a remote database integration, not embedded SQLite inside each serverless function.
Vercel on the AWS Marketplace: What the Listing Does to Procurement and Lock-In
Vercel has been on the AWS Marketplace since 2024. The real shift is that an EDP commit can absorb the spend, coupling the frontend host to AWS and deepening the lock-in.
Serving Cold MoE Models: CrossPool Disaggregates KV Cache and Weights
CrossPool splits MoE FFN weights and KV-cache into separate GPU pools and ships hidden states across the boundary, trading VRAM residency for an interconnect bottleneck.
Vercel's In-Function Concurrency: What It Does to Cold Starts and Billing
Vercel's in-function concurrency lets one warm instance serve many requests. Cold starts and idle-I/O bills drop, but CPU-bound handlers contend and shared state can race.
Poisoning a RAG Retriever: How Conflict-Aware Edits Inject False Knowledge
CAREATTACK (June 2026) edits RAG retriever weights to surface attacker-chosen passages, bypassing corpus defenses and moving the trust boundary onto the embedding model.
Vercel Raised Its CDN Origin Timeout to Two Minutes: What Breaks First
Vercel lifted its CDN origin timeout from 30 to 120 seconds, relocating rather than removing a failure boundary and holding wedged connections four times longer before a 504.
Gradio-Lite Runs Model Inference in the Browser via Pyodide, No Server
Gradio-Lite runs the Gradio Python runtime as WebAssembly via Pyodide, pushing inference into the visitor's browser with no server, bounded by CPU compute and browser memory.
Cloudflare AI Gateway Adds Spend Limits to Cap the Runaway Inference Bill
Cloudflare AI Gateway spend limits cap dollar spend per rule and return HTTP 429 when exceeded, turning cost control into an inline circuit breaker, not a billing alert.
Vercel Now Honors stale-if-error: Serving Stale Cache When the Origin Dies
Vercel's CDN now serves a cached copy when an origin fails, but only inside the stale-if-error window you set. It masks transient failures, it does not fix the origin.
Vercel's Manual CDN Purge API: Cache Control Without a Redeploy
Vercel's cache-tag purge API clears CDN, Runtime, and Data cache at runtime, no redeploy. The verb sets origin load: invalidate stays safe, dangerously-delete can stampede.
Cloudflare Now Routes Public Traffic to Private Apps via DNS, No VPN
Cloudflare's private-origins DNS routing lets public hostnames reach RFC 1918 apps without a VPN, but the flag only routes traffic; it does not authenticate callers.
GitHub's AI Capacity Crunch Pushes Microsoft to Rent AWS Compute
Microsoft reportedly rents AWS compute to keep GitHub's AI inference running after Azure fell behind, signaling that owned infrastructure no longer self-supplies AI load.
Cloudflare's Temporary Accounts Give AI Agents Disposable Credentials
Cloudflare's temporary accounts give agents auto-expiring 60-minute credentials, but the launch is an onboarding shortcut, not a scoped security control.
Running Long-Context Agents on a 4-Bit KV Cache: Where Accuracy Breaks
UltraQuant cuts agent time-to-first-token 3.47x with 4-bit KV caching on AMD CDNA4, but its June 2026 preprint omits the accuracy numbers operators need to ship it.
When LLM-Generated CUDA Kernels Pass Tests but Get the Math Wrong
LLM-written CUDA kernels compile, run, and pass smoke tests while returning wrong numerics, so crash-free execution is not enough to trust AI-generated GPU code.
Running GLM-5.2 at Home: SGLang, vLLM, Transformers, and KTransformers Setup Guide
GLM-5.2 weights are live on HuggingFace under MIT license: 753B MoE, 1M-token context, FP8 and BF16 variants. How to pick a deployment framework and model the hardware cost.
AWS Bedrock Now Requires Data Sharing for Mythos: The Self-Hosting Calculus
AWS Bedrock's provider_data_share gate for Mythos-class models removes the in-AWS data boundary regulated teams bought it for, pushing them toward self-hosted serving.
vLLM Cold Start Latency: Why Scale-to-Zero LLM Serving Stalls
A June 2026 MLSys paper breaks vLLM cold start into six CPU-bound boot phases, showing why scale-to-zero serving forces operators back into warm GPU pools.
The Vercel-AWS Deal Reveals Where AI Inference Runs
Vercel's May 2026 AWS databases integration clarifies where its AI workloads actually run: inference stays behind external APIs while the stateful tier moves to AWS regions.
