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/Inference

Inference

Reporting, analysis and primary-source coverage on Inference.

Latest coverage
LatestMost read
Intel Pushes Core Ultra Series 3 Into Humanoid and Commercial Robotics

Robotics & Defence

Intel Pushes Core Ultra Series 3 Into Humanoid and Commercial Robotics

Intel is pitching its 18A Core Ultra Series 3 (Panther Lake) processors to robotics builders seeking single-SoC CPU, GPU, and NPU consolidation.

Marcus Vance16 Nov

MAS Opens Future of Finance Institute With PathFin.ai and SafeFin.ai

Asia & SEA Tech

MAS Opens Future of Finance Institute With PathFin.ai and SafeFin.ai

Singapore's MAS launched the Future of Finance Institute under interim CEO Alan Lim to move banks from AI pilots to production under SAFR and MindForge.

Jin16 Nov

Google Launches Gemini Decisions API for 150ms Multimodal Routing

Agents & Tools

Google Launches Gemini Decisions API for 150ms Multimodal Routing

Google's Gemini Decisions API and gemini-decision-1 model process 1,000 classification questions in 150 to 250ms at $0.10 per million input tokens.

Clara Tan16 Nov

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

Infineon Produces First Functional 300mm Silicon Carbide Power Wafers in Villach

Chips & Compute

Infineon Produces First Functional 300mm Silicon Carbide Power Wafers in Villach

Infineon processed functional 300mm silicon carbide power devices in Villach using existing silicon fab tools, yielding 2.3 times more chips per wafer.

Jin15 Nov

Self-Hosted AI Agents Comparison 2026: OpenClaw vs Goose vs Agent Zero Architecture and Security

Enterprise & Cloud

Self-Hosted AI Agents Comparison 2026: OpenClaw vs Goose vs Agent Zero Architecture and Security

A technical comparison of OpenClaw, Goose, and Agent Zero, analysing IPC protocols, sandbox isolation, credential storage, and local resource utilisation.

Aarav Mehta15 Nov

Critical GPUStack RCE Vulnerability CVE-2026-102895 Exposes Enterprise AI Compute Clusters

Zero-Days & Patching

Critical GPUStack RCE Vulnerability CVE-2026-102895 Exposes Enterprise AI Compute Clusters

A critical unauthenticated remote code execution flaw in open-source orchestrator GPUStack allows threat actors to seize enterprise AI accelerator cluster…

Elena Rostova14 Nov

Google DeepMind Unveils Gemini Robotics 2.5 Vision-Language-Action Architecture for Dexterous Manipulation

Robotics & Defence

Google DeepMind Unveils Gemini Robotics 2.5 Vision-Language-Action Architecture for Dexterous Manipulation

DeepMind has released Gemini Robotics 2.5, unifying multimodal reasoning with high-frequency motor control trajectories for industrial robot manipulation.

Marcus Vance14 Nov

Brown University Physicists Eliminate AI Chip Dead Layer to Slash Neural Accelerator Power Draw

Chips & Compute

Brown University Physicists Eliminate AI Chip Dead Layer to Slash Neural Accelerator Power Draw

Brown University researchers have eliminated the dead-layer degradation in atomic-thin multiferroic films, opening a pathway to ultra-low-power AI process…

Marcus Vance14 Nov

Qualcomm Implements 10% Price Increase on PC Processors as Advanced Foundry Costs Escalate

Chips & Compute

Qualcomm Implements 10% Price Increase on PC Processors as Advanced Foundry Costs Escalate

Qualcomm has notified PC manufacturing partners of an upcoming 10% price increase across Snapdragon X-series processors due to rising advanced node foundr…

Marcus Vance14 Nov

Nvidia Approaches TSMC for Custom 3D DRAM Integration on Next-Generation AI Silicon

Chips & Compute

Nvidia Approaches TSMC for Custom 3D DRAM Integration on Next-Generation AI Silicon

Nvidia has initiated technical talks with TSMC to integrate custom 3D DRAM directly onto logic tiles, targeting the memory bandwidth wall in AI clusters.

Marcus Vance14 Nov

DayOne Secures $320M Round to Scale Enterprise Context Engines Across Asia-Pacific

Funding & Deals

DayOne Secures $320M Round to Scale Enterprise Context Engines Across Asia-Pacific

Enterprise AI platform DayOne has raised $320 million in growth funding to expand multilingual context engines for financial institutions across Asia-Paci…

Jin14 Nov

Tags on this page

  • Hardware5
  • Semiconductors4
  • AI3
  • AI Hardware2
  • Comparison2
  • Guide2
  • Robotics2
  • Startups2
  • 300MM1
  • 3D Dram1
  • Agent-zero1
  • Agents-tools1
← Previous

Page 1 of 4

Next →