RadixArk
@radixark
Miles runs RL end to end on NVIDIA Vera Rubin, out of the box: SGLang rollouts, Megatron training, one container image. And agentic RL with 64 concurrent sandboxes on the Vera CPU, right next to the GPUs. Thanks to @NVIDIAAI for the early access. Details in the blog 👇
SGLang@sgl_project · Oct 9We brought SGLang to NVIDIA Vera Rubin and accelerated Kimi K3 inference.
Working closely with @nvidia, we optimized attention, MoE, and speculative verification kernels on early-access Rubin hardware.
Highlights:
• Up to 20% faster FP8 MLA at batch 1 / 128K context
• 20%
Open quoted post →Working closely with @nvidia, we optimized attention, MoE, and speculative verification kernels on early-access Rubin hardware.
Highlights:
• Up to 20% faster FP8 MLA at batch 1 / 128K context
• 20%
1 33