SGLang is a high-performance serving framework for large language models and multimodal models.
[NPU] --attn-cp-size --init-expert-location --eplb-algorithm parameter docs update (#22704)
Co-authored-by: Jianzhao Xu <xujianchao@huawei.com>
J
jianzhao-xu committed
b6a91b1afefc3caac396f720aa9beeb798aabf75
Parent: 8d904e5
Committed by GitHub <noreply@github.com>
on 4/13/2026, 2:42:34 PM