AI Briefing#pcie
The latest AI and developer news about #pcie, with the original source and a short summary.
The latest AI and developer news about #pcie, with the original source and a short summary.
In PCIe-based VLA training, FP8 transmission reduced bytes by 48.4%, but step time increased because post-merger serialization placed it on the critical path.
Nvidia has disclosed the hardware requirements for running CUDA on RISC-V server CPUs.
AMD has unveiled the MI350P PCIe AI GPU, which can be plugged into existing servers.
AMD has unveiled the CDNA 4-based Instinct MI350P PCIe accelerator.
A PoC that reduces PCIe bottlenecks using NVENC was released along with real-world measurement results for its compression approach.
Verified Qwen3.5-122B running at 198 tok/s on 2x RTX PRO 6000 Blackwell.