Profiling LLM Inference with SGLang and Torch Profiler
This blog is my attempt to learn how to profile an llm served using sglang and its in built torch profiler integration that comes out of box...
Topic
#FlashInfer
2 篇笔记
Kimi K3 Is Here: Efficient Day-0 Support on vLLM
vLLM delivers day-0 Kimi K3 serving with hybrid KDA prefix caching, DSpark speculative decoding, production-scale disaggregation, and optimized kernels across N