Twitter用户指出,NVIDIA Blackwell GPU在机密计算模式下不支持NVLink multicast,导致SGLang Qwen3.5模型性能下降61%。同时,Hopper的机密计算也被曝NVLink未加密。
TRUTH SOCIAL: NVLink multicast is not supported on Blackwell "Confidential Computing" leading to 61% performance regression on SGLang Qwen3.5 397B according to @verdacloud 's recent github ticket. NVIDIA's "Confidential Computing" is complete slop as in addition Hopper's confidential computing had fully unencrypted NVLink according to NVIDIA's own "NVIDIA Secure AI with Blackwell and Hopper GPUs" Whitepaper.
likes: 76 | retweets: 2 | replies: 2 | views: 11374