Oops! That page is private.

Take me home

Popular topics

DGX Spark (SM121) Software Support is Severely Lacking - Official Roadmap NeededDGX Spark / GB10
How to run GLM 4.7 on dual DGX Sparks with vLLM / mods support in spark-vllm-dockerDGX Spark / GB10
DGX Spark Multi-Node LLM Inference Report for Qwen3-235B modelDGX Spark / GB10
DGX Spark, Nemotron3, and NVFP4: Getting to 65+ tpsDGX Spark / GB10
NVIDIA folks – where is this promised nvfp4 speedup?DGX Spark / GB10
Buyers beware: DGX Spark limited to 64GB in ComfyUIDGX Spark / GB10
Can someone with 2 Sparks benchmark NVFP4 MiniMax M2.1 quant?DGX Spark / GB10
Has Anyone Tried Getting ~1.5×+ Speedup on DGX/Spark/Grace/Blackwell using this?DGX Spark / GB10
Unable to install nvidia-driver from debian 13 cuda repo due to hash sum mismatchLinux
From 20 to 35 TPS on Qwen3-Next-NVFP4 w/ FlashInfer 12.1fDGX Spark / GB10
More…

Recent topics

[Bug] TensorRT-LLM 1.2.0rc8: “TRTLLMGenFusedMoE does not support SM120” error on DGX Spark with gpt-oss-120b + Eagle3TensorRT for RTX
Nsight Systems: Unified Memory Trace Support for GB10 (SM121)DGX Spark / GB10
Jetson Dev Kits for College HackathonTaiwan
Does DGX Spark support HW security fuses?DGX Spark / GB10
xTTS in a Dockercontainer on the DGX SparkDocker and NVIDIA Docker
PCIe5 P2P GPU via NICs faster than PCIe switch?CUDA Programming and Performance
Issues when attempting to upload nvidia bug reportLinux
Chrome on spark?DGX Spark / GB10 Projects
ComfyUI: Anyone else having problems with LOW-pass CPU offloading?DGX Spark / GB10
Use of Rubberazer library on jetson orin nano to toggle JPIOJetson Orin Nano
More…