Netflix co-founder backs $312M round for optical inference appliance maker Olix
Artificial intelligence hardware startup Olix Computing Ltd. today announced that it has raised $312 million in funding. The Series C round included contributions from Arm Holding plc, Netflix Inc.
Key Takeaways
- SiliconANGLE UPDATED 18:33 EDT / AUGUST 03 2026 AI Netflix co-founder backs $312M round for optical inference appliance maker Olix by Maria Deutscher Artificial intelligence hardware startup Olix Computing Ltd.
- As a result, it can't fit in the underlying chip's internal SRAM memory.
Graphics cards address the challenge by offloading the KV cache to off-chip HBM memory.
- Olix stated that the DX-1 "holds a model in fast on-chip memory, SRAM, for higher energy efficiency and lower latency.
" The company plans to ship the chip as part of a data center appliance called the X-1.
- A traditional optical interconnect with a handful of high-speed channels encodes data into light using a technology called PAM4.
- Olix hopes to start shipping its chips in the first half of 2027.
Stats & Key Facts
- #today announced that it has raised $312 million in funding.
- #3 billion, about triple what it was worth after its previous raise in February.
- #] The post Netflix co-founder backs $312M round for optical inference appliance maker Olix appeared first on SiliconANGLE.
- #SiliconANGLE UPDATED 18:33 EDT / AUGUST 03 2026 AI Netflix co-founder backs $312M round for optical inference appliance maker Olix by Maria Deutscher Artificial intelligence hardware startup Olix Computing Ltd.
SiliconANGLE UPDATED 18:33 EDT / AUGUST 03 2026 AI Netflix co-founder backs $312M round for optical inference appliance maker Olix by Maria Deutscher Artificial intelligence hardware startup Olix Computing Ltd. today announced that it has raised $312 million in funding. The Series C round included contributions from Arm Holding plc, Netflix Inc.
co-founder Reed Hastings and several others. 3 billion, about triple what it was worth after its previous raise in February. When a large language model receives a prompt, it turns the text into a collection of mathematical values called a KV cache.
It then uses the KV cache to generate a prompt response. The latter phase of the inference workflow is known as the decode stage. London-based Olix is developing a chip called the DX-1 that is specifically optimized for decode workloads.
For more details please read the original article at SiliconANGLE AI.
Continue Learning
Comments
Sign in to join the conversation