SemiAnalysis published the first third-party inference results for Google's TPUv7 Ironwood, showing up to 50% better performance per dollar than NVIDIA's B200/B300 in apples-to-apples comparisons. The…
OpenAI revealed first benchmarks for its Jalapeño AI accelerator ASIC, developed with Broadcom and Celestica, showing 1.5 to 1.9× more AI work per watt at peak throughput, 1.7 to 3.6× lower end-to-end…
OpenAI published first benchmark results for its custom AI inference chip Jalapeño, co-developed with Broadcom, showing 1.5 to 1.9 times greater peak performance per watt than Nvidia Blackwell systems…
OpenAI announced its first custom inference chip, Jalapeño, on August 25, 2026, claiming it outperforms Nvidia's GB200 and GB300 accelerators by 1.5 to 1.9 times more AI work per watt and 1.7 to 3.6 t…
OpenAI's custom AI inference chip, Jalapeño, outperforms Nvidia's Blackwell system on SemiAnalysis' InferenceX benchmark, delivering higher tokens-per-user throughput and better efficiency (tokens per…
OpenAI said its Broadcom-built Jalapeño inference chip delivers 1.5 to 1.9 times more AI work per watt than Nvidia's GB200 and GB300 systems on tested models, with 1.7 to 3.6 times lower end-to-end la…
OpenAI has disclosed first measured results for its custom inference chip, Jalapeño, showing a 1.5 to 1.9 times increase in AI work per watt at peak throughput compared to leading commercial systems, …
OpenAI's Jalapeño inference chip outperformed Nvidia's Blackwell system on Semianalysis's InferenceX benchmark, delivering more tokens per user and more throughput per kilowatt, according to results p…
OpenAI's new inference chip, Jalapeño, outperforms Nvidia's Blackwell and other competitors in performance per watt across almost all scenarios, according to benchmarks run by SemiAnalysis with OpenAI…
SemiAnalysis's AgentX benchmark shows NVIDIA's Vera Rubin NVL72 delivers up to 30x higher AI-factory throughput per megawatt than GB300 NVL72 for agentic-coding inference, while GB300 NVL72 extends it…
SemiAnalysis, a semiconductor and AI research firm with 85 team members and 280,000 subscribers, presented 'From Fab to Token' at a conference, detailing the state of the AI hardware market. The prese…
Sail Research has open-sourced HTDYM (How To Deploy Your Model), an internal performance modeling infrastructure that helps determine the optimal hardware and sharding configuration for serving large …
SGLang achieved a 5x throughput improvement for serving DeepSeek-V4 on NVIDIA GB300 hardware since its Day-0 launch, reaching ~11,200 tok/s/GPU at 50 tok/s/user through kernel and runtime optimization…
DeepSeek v4, an open-source model from a Chinese lab, achieved a 100x performance improvement on AMD hardware within 26 days of its Day 0 release, driven by the AMD SGLang engineering team. The Infere…