@intel's Mingfei Ma covers SGLang on Intel GPUs and Xeon CPUs: attention, quantized kernels and graph execution.
Learn how serving optimizations differ for compact language models and diffusion workloads.
Intel's Mingfei Ma explains SGLang serving optimizations on Intel hardware
AIIntel's Mingfei Ma covers SGLang on Intel GPUs and Xeon CPUs, including attention, quantized kernels and graph execution. The post says serving optimizations differ for compact language models and diffusion workloads.
Source details
SGLang · x.comPublished · added here
Original title: @intel's Mingfei Ma covers SGLang on Intel GPUs and Xeon CPUs: attention, quantized kernels and graph execution.