gpudirect-storage

Here are 3 public repositories matching this topic...

SSHdotCodes / deepseek-v4.1-flash-pro6000

DeepSeek-V4.1-Flash-1017 at native precision on one RTX PRO 6000 + 128 GB RAM: 31.6 tok/s decode, 1M context. ds41d engine with VRAM/RAM/NVMe expert tiers, GPUDirect Storage and DSpark speculative decoding

cuda moe blackwell llm-inference speculative-decoding deepseek mxfp4 rtx-pro-6000 gpudirect-storage

Updated Oct 19, 2026
Python

aws-samples / sample-eks-vllm-gds-fsx-lustre

Star

Accelerate vLLM model loading on Amazon EKS using InstantTensor and NVIDIA GPUDirect Storage (GDS) with Amazon FSx for Lustre

model-loading amazon-eks fsx-lustre vllm llm-inference deepseek gpudirect-storage

Updated Sep 29, 2026
YAML

izzet / gdsight

Star

Per-operation cross-layer tracer for GPUDirect Storage

ebpf nvme cross-layer explainability cufile gpudirect-storage

Updated Oct 1, 2026
Python

Add this topic to your repo

To associate your repository with the gpudirect-storage topic, visit your repo's landing page and select "manage topics."

Learn more