Most companies overpay for AI inference by 2x to 5x, sometimes by an order of magnitude, because their inference stack doesn't match their use case priorities, said Meryem Arik, co-founder of inferenc…
A production configuration for running DeepSeek-V4-Flash-0731 on a single AMD MI300X GPU achieves 168.6 tok/s median single-stream decode and 542 tok/s aggregate across 8 concurrent streams, with the …
Doubleword, one of six companies in the first wave of UK Sovereign AI investments, achieved up to 3× the throughput of vLLM for DeepSeek-V4-Flash on a single node of Isambard-AI, the UK's national AI …
Four infrastructure experts discussed the challenges of scaling AI in production, noting that AI workloads are shifting from databases to tokens, creating unexpected bottlenecks in cost, reliability, …
Doubleword released an open-source agent swarm that lets an LLM orchestrator design its own team of bounded-context workers to parallelize wide, shardable tasks. In a security audit of a 2.4M-token co…
A viral chart predicting open-weights AI models will catch closed frontier models by December 2026 is misleading, as analysis across 18 benchmarks shows the gap varies by task and is not uniformly shr…
Researchers at Doubleword developed UCCL-EP, an expert parallel communications kernel that enables GPU-initiated communication patterns like DeepEP to work across arbitrary NIC-accelerator pairs, incl…
AMD's MI300X accelerator, with 192GB of HBM3 memory and roughly half the list price of NVIDIA's H100, remains underutilized due to software incompatibilities. As of early May 2026, running vLLM with D…
Meryem Arik, CEO of Doubleword, presented on the importance of AI model gateways as a solution for managing the complexity that arises when decentralized teams use multiple inference providers (like O…