Topics
Results for “distributed inference”
5 results
- Serving GLM-5.3 at 607.8 tok/s across two Nvidia DGX stations with vLLM — 2 sources · Seen
- NVIDIA Dynamo Recipes Bring Korea’s Leading Open Models to Production — NVIDIA Blog · Seen
- Wave Forcing: Towards Speed-of-Light Streaming Video Generation — Hugging Face Papers · Seen · 126 points
- Distributed LLM Inference via Communication-Efficient Speculative Decoding — arXiv AI Papers · Seen
- TRACE: Transformer Residual Activation Codebook Encoding for Communication-efficient Distributed Edge Inference — arXiv AI Papers · Seen