# jetstream

JetStream is a throughput- and memory-optimized engine for LLM inference on XLA devices, with reference implementations for JAX and PyTorch models.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## TorchTPU - A Hybrid Eager/Compiled Architecture for Native PyTorch Execution on TPU

DevFeed: [TorchTPU - A Hybrid Eager/Compiled Architecture for Native PyTorch Execution on TPU](<https://devfeed.tech/articles/torchtpu-a-hybrid-eager-compiled-architecture-for-native-pytorch-execution-on-tpu-97999.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.24161>)

Author: Claudio Basile, Michael Voznesensky, Gunhyun Park, Ben Wilson, Parker Holloway, Zhanyong Wan, Vlad Belous, Manish Khanna, Paul Ganssle, Kevin Gleason, Andrew Dame, Brendan Folie, Bhavya Bahl, Haifeng

Published: 2026-10-23T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [PyTorch](<https://devfeed.tech/topics/pytorch.md>), [jetstream](<https://devfeed.tech/topics/jetstream.md>)

Tags: [backend](<https://devfeed.tech/tags/backend.md>), [collaboration](<https://devfeed.tech/tags/collaboration.md>), [compile](<https://devfeed.tech/tags/compile.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [execution](<https://devfeed.tech/tags/execution.md>), [google](<https://devfeed.tech/tags/google.md>), [hardware-acceleration](<https://devfeed.tech/tags/hardware-acceleration.md>), [inference](<https://devfeed.tech/tags/inference.md>), [meta](<https://devfeed.tech/tags/meta.md>), [migration](<https://devfeed.tech/tags/migration.md>), [model](<https://devfeed.tech/tags/model.md>), [native](<https://devfeed.tech/tags/native.md>), [optimizations](<https://devfeed.tech/tags/optimizations.md>), [performance](<https://devfeed.tech/tags/performance.md>), [pytorch](<https://devfeed.tech/tags/pytorch.md>), [torchtpu](<https://devfeed.tech/tags/torchtpu.md>), [tpu](<https://devfeed.tech/tags/tpu.md>), [training](<https://devfeed.tech/tags/training.md>)

### AI overview

TorchTPU is an open-source Google-Meta project providing a native PyTorch backend for Google TPUs. It aims to support out-of-the-box model execution and migration to TPU, combining eager execution optimizations, torch.compile integration, and native hardware acceleration. The supplied abstract claims industry-competitive inference and training performance but gives no benchmark details.

### Source excerpt

arXiv:2610.24161v3 Announce Type: replace Abstract: TorchTPU is an open-source collaboration between Google and Meta that introduces a native and principled PyTorch backend for Google TPUs. It enables seamless out-of-the-box model execution and TPU migration while delivering industry-competitive inference and training performance through eager execution optimizations, torch.compile integration, and native hardware acceleration.

## wasmCloud 2.9: NATS-native interfaces, guest memory enforcement, and Kubernetes-grade lifecycle

DevFeed: [wasmCloud 2.9: NATS-native interfaces, guest memory enforcement, and Kubernetes-grade lifecycle](<https://devfeed.tech/articles/wasmcloud-2-9-nats-native-interfaces-guest-memory-enforcement-and-kubernetes-grade-lifecycle-15445.md>)

Original publisher: [Read original article](<https://wasmcloud.com/blog/wasmcloud-2-9-release/>)

Author: Eric Gregory

Published: 2026-09-08T00:00:00Z

Content type: release

Language: en

Sources: [wasmCloud](<https://devfeed.tech/sources/wasmcloud-blog.md>)

Topics: [jetstream](<https://devfeed.tech/topics/jetstream.md>), [Kubernetes](<https://devfeed.tech/topics/kubernetes.md>), [Messaging](<https://devfeed.tech/topics/messaging.md>), [configuration](<https://devfeed.tech/topics/configuration.md>)

Tags: [configuration](<https://devfeed.tech/tags/configuration.md>), [jetstream](<https://devfeed.tech/tags/jetstream.md>), [kubernetes](<https://devfeed.tech/tags/kubernetes.md>), [messaging](<https://devfeed.tech/tags/messaging.md>), [release](<https://devfeed.tech/tags/release.md>), [updates](<https://devfeed.tech/tags/updates.md>)

### AI overview

wasmCloud 2.9.0 introduces a NATS-native interface with access to Core NATS, JetStream, and key-value buckets. The release also enforces guest memory budgets in real time, adds Kubernetes-oriented lifecycle behavior, allows idle instance pools to shrink, enables guest execution metrics by default, and unifies host plugin configuration.

### Source excerpt

wasmCloud 2.9 ships the NATS-native wasmcloud:nats interface with JetStream and key-value access, makes the guest memory budget enforceable, lets idle instance pools shrink, and teaches host pods to drain, probe, and survive control plane outages.

## Migrating from NATS to Redpanda: Evolve from messaging to streaming

DevFeed: [Migrating from NATS to Redpanda: Evolve from messaging to streaming](<https://devfeed.tech/articles/migrating-from-nats-to-redpanda-evolve-from-messaging-to-streaming-12716.md>)

Original publisher: [Read original article](<https://www.redpanda.com/blog/migrate-nats-jetstream-messaging-to-streaming>)

Author: Kavya Shivashankar

Published: 2025-11-18T00:00:00Z

Content type: article

Language: en

Sources: [Redpanda](<https://devfeed.tech/sources/redpanda.md>)

Topics: [Messaging](<https://devfeed.tech/topics/messaging.md>), [Event-Streaming](<https://devfeed.tech/topics/event-streaming.md>), [jetstream](<https://devfeed.tech/topics/jetstream.md>), [event driven](<https://devfeed.tech/topics/event-driven.md>), [data-platforms](<https://devfeed.tech/topics/data-platforms.md>), [Microservices](<https://devfeed.tech/topics/microservices.md>), [Persistence](<https://devfeed.tech/topics/persistence.md>), [real-time](<https://devfeed.tech/topics/real-time.md>), [Latency](<https://devfeed.tech/topics/latency.md>), [personalization](<https://devfeed.tech/topics/personalization.md>)

Tags: [database](<https://devfeed.tech/tags/database.md>), [event-driven](<https://devfeed.tech/tags/event-driven.md>), [event-streaming](<https://devfeed.tech/tags/event-streaming.md>), [jetstream](<https://devfeed.tech/tags/jetstream.md>), [latency](<https://devfeed.tech/tags/latency.md>), [messaging](<https://devfeed.tech/tags/messaging.md>), [microservices](<https://devfeed.tech/tags/microservices.md>), [persistence](<https://devfeed.tech/tags/persistence.md>), [personalization](<https://devfeed.tech/tags/personalization.md>), [pipelines](<https://devfeed.tech/tags/pipelines.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [streaming](<https://devfeed.tech/tags/streaming.md>)

### AI overview

This article explains how organizations can migrate from NATS and JetStream messaging to Redpanda Streaming as their systems grow from low-latency message delivery toward durable event streaming. It compares messaging and streaming requirements and presents Redpanda Connect as a way to simplify the migration.

### Source excerpt

Organizations are moving from message delivery to data streaming, unlocking new capabilities, insights, and improved business value. Here's how to do the same.

## Security: Fortify 1.7.4. Released

DevFeed: [Security: Fortify 1.7.4. Released](<https://devfeed.tech/articles/security-fortify-1-7-4-released-3899.md>)

Original publisher: [Read original article](<https://laravel.com/blog/security-fortify-174-released>)

Author: Taylor Otwell

Published: 2021-01-07T18:50:00Z

Content type: release

Language: en

Sources: [Laravel Blog](<https://devfeed.tech/sources/laravel-blog.md>)

Topics: [Laravel](<https://devfeed.tech/topics/laravel.md>), [Security](<https://devfeed.tech/topics/security.md>), [Vulnerabilities](<https://devfeed.tech/topics/vulnerabilities.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>), [jetstream](<https://devfeed.tech/topics/jetstream.md>)

Tags: [jetstream](<https://devfeed.tech/tags/jetstream.md>), [laravel](<https://devfeed.tech/tags/laravel.md>), [pull-request](<https://devfeed.tech/tags/pull-request.md>), [security](<https://devfeed.tech/tags/security.md>), [update](<https://devfeed.tech/tags/update.md>), [vulnerability](<https://devfeed.tech/tags/vulnerability.md>)

### AI overview

Laravel Fortify 1.7.4 addresses a potential security vulnerability introduced in Fortify 1.7.3. Applications using Fortify 1.7.3, including Jetstream-based applications, should be updated.

### Source excerpt

We have reverted a pull request that was merged into Laravel Fortify 1.7.3 which introduced a potential security vulnerability. Please update your applications using Fortify 1.7.3, including all Jetst...