#server-npus

#server-npus

"Snowflake gives customers one place to bring their data together, connect the systems they rely on, and turn AI into something that actually helps teams get work done," says Baris Gultekin, VP of AI at Snowflake.

"Claude has regressed to the point it cannot be trusted to perform complex engineering," an AMD senior director wrote in a widely shared post on GitHub.

The Xeon 600 lineup spans the gamut between 12 and 86 performance cores (no cut-down efficiency cores here), with support for between four and eight channels of DDR5 and 80 to 128 lanes of PCIe 5.0 connectivity. Compared to its aging W-3500-series chips, Intel is claiming a 9 percent uplift in single threaded workloads and up to 61 percent higher performance in multithreaded jobs, thanks in no small part to an additional 22 processor cores this generation.

Four generations, MTIA 300, 400, 450, and 500, have been produced within less than two years, with several already in production and others scheduled for mass deployment in 2026 and 2027. The quick pace is deliberate. Rather than betting on a single chip generation and waiting years for results, Meta has adopted a roughly six-month cadence per generation, using modular chiplet architecture to enable incremental upgrades without replacing entire rack systems.

What we are beginning to see is that many open-source and other models are becoming compact enough and sufficiently optimized to run very efficiently on consumer GPUs,

The company, which is based in San Francisco and has an office in Pune, India, is targeting up to $35 million this year as it builds a royalty-driven on-device AI business. That growth has buoyed the company, which now has post-money valuation of between $270 million and $300 million, up from around $100 million in its 2022 Series B, Kheterpal said.

The new capabilities center on two integrated components: the Dynamo Planner Profiler and the SLO-based Dynamo Planner. These tools work together to solve the "rate matching" challenge in disaggregated serving. The teams use this term when they split inference workloads. They separate prefill operations, which process the input context, from decode operations that generate output tokens. These tasks run on different GPU pools. Without the right tools, teams spend a lot of time determining the optimal GPU allocation for these phases.