Quantum
Q.ANT Demonstrates Hybrid Photonic-GPU System for Language Models
Publication: The Quantum Insider
Author: Matt Swayne
Source published: 17/11/2026, 17:47:39 UTC
Briefing created: 17/11/2026, 19:51:39 UTC
Based on a feed excerpt; full article content has not been acquired. Source evidence retrieved 17/11/2026, 18:19:25 UTC.
Briefings
Q.ANT unveiled the NPU Gen 2+ photonic processor at SC26 in Chicago, adding optical Discrete Fourier Transforms (DFTs) to support AI. The company demonstrated a hybrid system coupling the NPU Gen 2+ with an AMD GPU to run a large language model for the first time, successfully replacing a computationally intensive attention layer. Q.ANT plans to offer commercial systems combining Gen 2 and Gen 2+ processors in the second half of 2027.
Key points
- Q.ANT unveiled the NPU Gen 2+ photonic processor at SC26 in Chicago, adding optical Discrete Fourier Transforms (DFTs) to support AI.
- The company demonstrated a hybrid system coupling the NPU Gen 2+ with an AMD GPU to run a large language model for the first time, successfully replacing a computationally intensive attention layer.
Context
Q.ANT is a pioneer in commercial photonic computing, extending its software toolkit to support the new capabilities. The demonstration at SC26 showed how photonic computing can replace classical attention layers, potentially lowering energy consumption and operating costs for data center operators.
Limitations
The evidence is limited to the SC26 demonstration and press release text. It does not include specific performance metrics, energy savings figures, or commercial launch dates beyond the 2027 roadmap. The source text is truncated at the end, cutting off mid-sentence regarding the integration method.
Generated by Bittrees-hosted qwen35-2b sha256:aaf42c8b7c3c on 17/11/2026, 19:51:39 UTC. Based on publisher-provided feed evidence; may not cover the full original article. Check the source for details.
View archived briefing on IPFS
bafybeihaihcypyxmezsisjdwgoiilwmyvupj4zaf7pq3srvy7h7mzemb5m