Perplexity Details Its GPU Embedding Stack: How Ivy, Tulip and ROSE Serve pplx-embed
Retrieval quality in an AI search product is bounded by two things: how good the embedding model is, and how cheaply you can run it across an index. This week, Perplexity Engineering team published Fast Embeddings on GPUs, an under-the-hood account of the second — the serving infrastructure behind pplx-embed and the ranking models used across Perplexity Search, Computer and the API Platform. Perplexity team states that embedding inference on the GPU side has largely converged across engines
Perplexity published technical details about its internal infrastructure for running embedding models on GPUs, which consists of three services: Ivy handles request parsing and load balancing, Tulip manages scheduling and batching, and ROSE executes the actual model inference. The quality of an AI search product depends on both the embedding model itself and how efficiently it can run across large indexes, making this serving infrastructure critical to performance. Rather than building a separate embedding engine, Perplexity reused its existing LLM kernels since embedding models behave similarly to LLM prefill and decode operations. The system uses techniques like CUDA graphs and lazy tensor management to reduce overhead from CPU-side work, allowing the infrastructure to efficiently handle different traffic patterns from batch indexing to real-time query embedding.
One short email a day with the stories that matter. Free. Unsubscribe with one click.
Want to go deeper than the news? Explore live, cohort-based AI courses taught by practitioners.
Browse AI courses on Maven
Google Unveils TPU 8i Max and TPU 8tx: A Dual-Chip TPU and a Confidential TPU
Google has added two new systems to its eighth-generation TPU lineup. TPU 8i Max targets massive context windows and rack density. TPU 8tx targets secure, confidential inference. Google TPU 8i Max is a dual-chip package built from 2 TPU 8i chips. Both arrive alongside TPU 8t and TPU 8i, announced in April. TL;DR Size: TPU 8i Max = 2 TPU 8i chips in 1 package. TPU 8tx = TPU 8t silicon plus 5th Gen AMD EPYC hosts. Runs on: Google Cloud TPU systems. Performance: 8i Max doubles TPU 8
Also reported by Data Center Knowledge
IBM Announces IBM Quantum Nighthawk r3: A New Processor to Support 10k Quantum Operations on 520 Programmable Qubits
IBM has announced IBM Quantum Nighthawk r3, its next superconducting quantum processor. It is designed to run 10,000 quantum operations accurately across 520 programmable qubits. In 2027, IBM plans to link 2 r3 chips into a single 1,040-qubit system. For developers, the announcement is speed. The current Nighthawk r2 already runs workloads up to 19x faster than IBM’s earlier processors. TL;DR Size: Nighthawk r3: 520 programmable qubits, 2,034 physical qubits, 10 l-couplers. Nightha
Why the data center you dread might never even be built
The data center boom is running into serious real-world obstacles, from widespread local opposition and permitting delays to a scramble for electricity. Before those challenges even come into play, though, there’s a more basic problem: A lot of the projects being announced may never get built in the first place. With billions of dollars in AI infrastructure […]
How backlash and red tape continue to slow data centers post-Blue Wave
The data center boom is running into serious real-world obstacles, from widespread local opposition and permitting delays to a scramble for electricity. Before those challenges even come into play, though, there’s a more basic problem: A lot of the projects being announced may never get built in the first place. With billions of dollars in AI infrastructure […]
AMD Launches Epyc SP7, Helion as AI Rack Demand Rises
AMD has begun shipping sixth-gen Epyc servers and is rolling out Helion AI racks, signaling a bigger push into enterprise and agentic AI infrastructure.
Google broadens its AI hardware portfolio with two new specialized chips
Google's new tensor processing units (TPUs) broaden its chip portfolio to more use cases: confidential model training and more memory capacity.