About this skill
NVIDIA Inference Xfer Library (NIXL) operator + developer reference. Point-to-point KV-cache and tensor transport for distributed inference (Dynamo, vLLM, SGLang). Covers the C++/Python/Rust agent API, all 13 backend plugins (UCX, GDS, GDSMT, libfabric, mooncake, posix, hf3fs, obj/S3, azureblob, gusli, uccl, gpunetio/DOCA, telemetry), build paths (pip nixl-cu12/cu13, meson+ninja from source), ETCD vs side-channel metadata, telemetry (Prometheus + cyclic shared-memory), NIXL-EP elastic MoE device kernels, and Dynamo / vLLM NixlConnector / SGLang integration patterns.
Quick start
- Copy the install prompt. Use the green button above this README.
- Send it to your agent. Paste it into your coding agent’s chat and send.
- Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
Review, license & listing details
This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.
Unsupported source URL
About scan coverage and limitationsAbout this listing
- Category
- Developer tools
- Reported license
- Not specified
- Listing language (estimated)
- English
- Review status
- Not individually reviewed
- Agent compatibility
- Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.