Cerebras Systems' CS-4 rack achieves 85% model flops utilization (MFU) on a 400B parameter training run across 16 systems, compared to 30-40% for traditional GPU clusters, thanks to the WSE-3's on-waf…
SGLang, an open-source LLM inference engine, introduces RadixAttention for prefix caching and grammar-constrained decoding, achieving 25x throughput improvement over vLLM for structured output tasks. …
A new benchmark evaluating DocumentAI models on bounding box accuracy shows GPT-5.5 and Gemini 3.5 leading with 67.7% and 67.5% scores respectively, while Qwen, Kimi, and Mistral trail significantly. …
Malte Buettner benchmarked bounding box accuracy for Document AI models using pages from the FlashAttention-3 paper, testing Qwen, Kimi, and Mistral via OpenRouter. The evaluation scored models on cov…