Qwen3.5 Inference Performance Engineering on Hygon DCU: From Prefill/Decode Hotspots to End-to-End Gains
AbstractIn large-model inference optimization, one of the easiest things to misinterpret is treating a local speedup of a certain kernel directly as an improvement in service throughput. Even if a kernel is 1.08x faster in isolated tests, the complete service may be only a few percent faster, or ...


