Compare LLM inference frameworks for production serving, request batching, KV cache management, and efficient deployment.
Official implementation of BrepCoder (ECCV 2026). This trains BrepCoder to generate Python-like CAD code from B-rep graphs. The default configuration is DeepSpeed ZeRO-2 on 4 GPUs, a batch size of 16 ...
The balance python package offers a simple workflow and methods for dealing with biased data samples when looking to infer from them to some target population of interest.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results