Kog AI — Web Pulse coverage

Real-time LLM Inference on Standard GPUs: 3k tokens/s per request :: https://wpnews.pro/news/real-time-llm-inference-on-standard-gpus-3k-tokens-s-per-request
Building a single-kernel, latency-optimized LLM inference engine on AMD MI300X GPUs :: https://wpnews.pro/news/building-a-single-kernel-latency-optimized-llm-inference-engine-on-amd-mi300x