Commentary: AMD's Taalas acquisition echoing Jensen Huang's Groq strategy
DIGITIMESen

On February 20, 2026, Canadian AI chip startup Taalas unveiled its HC1 inference chip. Taalas said the chip ran the Llama 3.1 8B model at a single-user inference speed of 16,960 tokens per second, roughly 48 times the inference speed of an Nvidia B200 in the company's testing.
This is a short summary published by AI Global Wire. The full article is owned and hosted by DIGITIMES — open it there to read it in full.
Read the full story at DIGITIMES- Meta
- Företag
Related AI news
- Task- and Session-Level Model Routing: A Common-Interface Hybrid Evaluation of Four Open-Source Routers Across Four BenchmarksarXiv cs.AI · August 18, 2026
- Position: Evaluations of AI Moral Reasoning Still Miss Half of the PicturearXiv cs.AI · August 18, 2026
- Anthropic 第二季營收暴增 14 倍且獲利轉正,最快秋天 IPOTechNews (TW) · August 18, 2026
- Anthropic revenue run rate surpasses $65b ahead of IPOTech in Asia · August 18, 2026
- US AI startup Higgsfield raises $400m series BTech in Asia · August 18, 2026
- Nvidia to back AI chip startup Groq at $3.5b valuationTech in Asia · August 17, 2026