TechWhoKnows
Log inSign up
Latest
AI
Startups
Venture
Tech
Security
Hardware
Biotech & Climate
Markets & Policy
Companies
TopicsNewsletterAbout
TechWhoKnows

Independent tech news from Singapore, with the sources linked.

Sections

  • AI
  • Startups
  • Venture
  • Tech
  • Security
  • Hardware
  • Biotech & Climate
  • Markets & Policy

TechWhoKnows

  • Companies
  • About
  • Newsletter
  • All topics
  • Search
  • Account

© 2026 TechWhoKnows. All rights reserved.

  • Privacy
  • Terms
Home/Topics/LLMs

LLMs

Reporting, analysis and primary-source coverage on LLMs.

Latest coverage
LatestMost read
vLLM vs SGLang vs TensorRT-LLM (2026 Comparison): Throughput, KV Caching, and Security

Agents & Tools

vLLM vs SGLang vs TensorRT-LLM (2026 Comparison): Throughput, KV Caching, and Security

Compare vLLM, SGLang, and TensorRT-LLM in 2026 across PagedAttention, RadixAttention prefix caching, TensorRT compilation, and inference server security.

Jin15 Nov

Apple Targets Local AI Developers With M6 14-Inch MacBook Pro Featuring Dual Neural Engines

Devices & Gadgets

Apple Targets Local AI Developers With M6 14-Inch MacBook Pro Featuring Dual Neural Engines

Now shipping across 35 countries starting at $1,999, Apple's 14-inch MacBook Pro with M6 packs GPU Neural Accelerators and 170GB/s memory bandwidth for lo…

Jin13 Nov

LMSYS Launches SGLang Inference Consortium With Nvidia, AMD, Intel, Google and Meta

Chips & Compute

LMSYS Launches SGLang Inference Consortium With Nvidia, AMD, Intel, Google and Meta

At the SGLang Summit in San Francisco, LMSYS Org formed the SGLang Consortium alongside major silicon and cloud providers to standardise open-source AI in…

Marcus Vance13 Nov

Why NVIDIA Cosmos and Cadence Just Solved Robotics’ Biggest Problem

Robotics & Defence

Why NVIDIA Cosmos and Cadence Just Solved Robotics’ Biggest Problem

We’ve mastered text and image generation, but making robots work reliably in the real world is a completely different beast. Here is why the newly expande…

Jin18 Apr

Bye Bye Llama, Hello Muse Spark

Models & Research

Bye Bye Llama, Hello Muse Spark

Meta is betting that social context beats raw parameters, pivoting away from its open-source legacy to win the AI platform war through proprietary "person…

Jin9 Apr

The $45 Million Per Month Bottleneck: How Ritivel AI Automates Drug Submissions

Biotech & Health

The $45 Million Per Month Bottleneck: How Ritivel AI Automates Drug Submissions

Discover how Ritivel AI is solving the pharmaceutical industry's multi-billion dollar regulatory bottleneck with highly traceable generative AI tailored f…

Jin23 Mar

Rocket.new Review: The Palo Alto AI App Builder Shipping Full-Stack Software

Funding & Deals

Rocket.new Review: The Palo Alto AI App Builder Shipping Full-Stack Software

Hands-on review of Rocket.new, the Palo Alto AI software builder: how it generates production full-stack apps past day one and how it compares with Lovabl…

Jin21 Mar

Tags on this page

  • Nvidia2
  • Open-source2
  • SGLang2
  • AI1
  • AI in Healthcare1
  • AMD1
  • Anthropic1
  • Apple1
  • Apple Silicon1
  • Cadence1
  • Clinical Trials1
  • Comparison1