⚡ A seamless integration of HuggingFace Transformers & Diffusers with RBLN SDK for efficient inference on RBLN NPUs.
-
Updated
Aug 28, 2026 - Python
⚡ A seamless integration of HuggingFace Transformers & Diffusers with RBLN SDK for efficient inference on RBLN NPUs.
PyTorch extension for Rebellions NPU
Prefill/decode disaggregation for LLM serving on RBLN-CA25 NPUs (vllm_rbln optimum path) + heterogeneous GPU→NPU KV bridge (dlfloat16, verified cos=0.9997). Deployable kits with paste-in runbooks.
Add a description, image, and links to the rbln topic page so that developers can more easily learn about it.
To associate your repository with the rbln topic, visit your repo's landing page and select "manage topics."