Hacker News: Front Page 2026-06-10 16:04 Anatomy of a high-performance EP kernel Open original source ↗ Reindex This Article Article URL: https://fergusfinn.com/blog/anatomy-of-a-high-performance-ep-kernel/ Comments URL: https://news.ycombinator.com/item?id=48478396 Points: 9 # Comments: 1
Show HN: Tiny-vLLM – high performance LLM inference engine in C++ and CUDA Hacker News: Front Page • similarity 0.432
How LinkedIn Identified a Kernel Lock Contention Issue Causing Recurring System Freezes InfoQ • similarity 0.423
Rotary GPU: Exploring Local Execution for Large MoE Models Under Limited VRAM Hacker News: Front Page • similarity 0.414
Real-time LLM Inference on Standard GPUs: 3k tokens/s per request Hacker News: Front Page • similarity 0.393
No comments yet.