rihard7854@alien.topB to LocalLLaMA@poweruser.forumEnglish · 10 months agoNVidia H200 achieves nearly 12,000 tokens/sec on Llama2-13B with TensorRT-LLMgithub.comexternal-linkmessage-square23fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkNVidia H200 achieves nearly 12,000 tokens/sec on Llama2-13B with TensorRT-LLMgithub.comrihard7854@alien.topB to LocalLLaMA@poweruser.forumEnglish · 10 months agomessage-square23fedilink
minus-squareLongjumping-Bake-557@alien.topBlinkfedilinkEnglisharrow-up1·10 months agoAnd that’s on a die just slightly bigger than the 4090. Unless they increased the size compared to h100?
And that’s on a die just slightly bigger than the 4090. Unless they increased the size compared to h100?