yuria retweeted
Replying to @hlslyuri @johnsmithyson0
ya i’ve been inside of yuria thats how close we are
i met @wandering_mush but i forgot to bring a second phone so u guys can all just have this photo
3
33
945
yuria retweeted
“The last thing a model sees before being captured in a cuda graph.”
The only thing faster than GB300 Dynamo + vLLM is Vera Rubin Dynamo + vLLM 🏎️💨.
The first DeepSeek V4.1 Flash results on @NVIDIA Vera Rubin NVL72 are here, powered by Dynamo + vLLM on @SemiAnalysis_'s AgentX benchmark.
Compared with GB300 NVL72 running Dynamo + vLLM, InferenceX's perf ruler shows:
• 63.4× total token throughput per chip at 400 tok/s/user
• 93.3× at 600 tok/s/user

















