@QuixiAI: Two fixes for the NVIDIA open kernel driver on DGX Spark - Freed GPU memory now returns to the OS when a process exits …
Summary
NVIDIA's open kernel driver for DGX Spark received two fixes that return freed GPU memory to the OS when a process exits and enable huge pages for GPU page faults on system memory, boosting first-touch bandwidth from 0.4 to 19.6 GiB/s.
Similar Articles
@QuixiAI: Like this is a legit bug DGX spark should get latest cuda the *instant* it's released @nvidia
A bug has been identified in DGX Spark, with the author urging NVIDIA to ensure it receives the latest CUDA updates without delay.
@QuixiAI: https://x.com/QuixiAI/status/2092804334417236135
This is a fork of NVIDIA's open GPU kernel modules that enables PCIe peer-to-peer communication between consumer GeForce GPUs (3090, 4090, 5090), significantly improving multi-GPU performance by allowing direct data transfer over PCIe.
@QuixiAI: I finally got a dgx spark First thing I noticed - they make it hard to install latest cuda. I might need to install van…
User @QuixiAI reports difficulty installing the latest CUDA toolkit on their NVIDIA DGX Spark, suggesting that installing vanilla Ubuntu may be necessary to resolve the issue.
@svpino: We are getting 2 new devices from NVIDIA and Microsoft: 1. The DGX Station, with GB300 superchip and up to 748GB of mem…
NVIDIA and Microsoft are releasing two new AI hardware devices: the DGX Station with GB300 superchip and 748GB memory, and the RTX Spark laptop with 1 petaflop AI performance and 128GB unified memory.
@no_stp_on_snek: It's still pretty awesome what a single spark can do. Thanks @NVIDIAAI
A user shares that they replicated running DeepSeek-V4-Flash-0731 on a DGX Spark using antirez's DwarfStar-4 setup, confirming impressive performance on a single device.