cd/entity/AMD MI300XΒ· homeβ€Ί entitiesβ€Ί AMD MI300X
grep -l @amd mi300x /news/*.json | wc -l β†’ 2

AMD MI300X

mentions 2 type Person feed RSS

// recent coverage 2 mentions

09:47
2026-05-29
blog.kog.ai
large-language-models

Real-time LLM Inference on Standard GPUs: 3k tokens/s per request

Kog AI launched a tech preview of its Kog Inference Engine (KIE), achieving 3,000 output tokens per second per request on 8Γ— AMD MI300X GPUs and 2,100 on 8Γ— NVIDIA H200 GPUs using a 2B model. The comp…

// co-occurs with top 7 entities