doca-gpi

SKILLWorkflowCommunity
v0.0.0NVIDIAApache-2.0Aktualisiert vor 6 TQuelle →

Use this skill for hands-on DOCA GPI programming — wiring a GPU-Packet-Initiator context so a CUDA kernel drives RDMA queues directly from GPU memory without host CPU mediation. Covers picking GPI vs doca-gpunetio, the doca_gpi / domain / channel object model, the GPU-side handle handoff (doca_gpu_g

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
3kRepo-Sterne
1Clients
1Formate
vor 6 TLetzte Aktualisierung
Skill
AutorNVIDIA
Version0.0.0
LizenzApache-2.0
KategorieWorkflow
Formateskill.md
PromptÖffnen (siehe Tab „Prompt“)
Kompatibilität
Claude✓ Unterstützt
Cursor
Copilot
ChatGPT
Gemini
Über

Use this skill for hands-on DOCA GPI programming — wiring a GPU-Packet-Initiator context so a CUDA kernel drives RDMA queues directly from GPU memory without host CPU mediation. Covers picking GPI vs doca-gpunetio, the doca_gpi / domain / channel object model, the GPU-side handle handoff (doca_gpu_gpi_channel*), attaching GPU memory to a GPI domain, the domain and channel attribute objects, and de

Schlagwörter
skillclaude