#Low Latency

AMD and Cerebras Team on AI Inference

AMD and Cerebras unveil a new AI inference solution combining AMD Helios GPUs with Cerebras' Wafer-Scale Engine for ultra-low latency and high throughput.

Real-Time Agentic AI Unlocked

New methods like Asynchronous I/O and Speculative Tool Calling slash latency for agentic AI, enabling real-time interactions on both cloud and edge devices.

Superhuman Hits 200K QPS With Databricks

Superhuman and Databricks engineers collaborated to build an AI inference platform serving over 200K QPS with sub-second latency.

Spark Streaming Hits Millisecond Latency

Databricks' Apache Spark Structured Streaming real-time mode is now GA, offering sub-second latency and consolidating streaming needs onto a single engine.

Spark Drops Microbatch for Real-Time

Apache Spark's Real-Time Mode (RTM) breaks microbatch barriers, enabling millisecond latency for streaming workloads with a new hybrid execution model.

Bridging DSP and DL for Speech Enhancement

TVF integrates DSP interpretability with deep learning's adaptability for low-latency, real-time speech enhancement, offering explicit control over spectral modifications.

Spark Ditches Dual Engines for Real-Time Mode

Databricks' new Real-Time Mode for Spark aims to deliver sub-second streaming speeds, eliminating the need for separate processing engines.

UCSD Lab Advances Low-Latency LLM Serving with DGX B200