Author

Didem Unat

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

GPU-Initiated Communication: Dissecting Down to the Bone

GPU-initiated communication lets GPU threads post RDMA operations directly to the NIC. It underpins NVSHMEM, NCCL GIN, and DeepEP, which serve the fine-grained, latency-critical communication of Mixture-of-Experts (MoE) models, yet its performance characteristics and optimizations remain scarcely documented beyond sour...

Javid Baydamirli, Ismayil Ismayilov, Kaan Oktay et al. · 0 citations

#machine learning Preprint Oct 2026

Static Bootstrap Placement for Encrypted Language Model Decoding

Language models increasingly serve prompts that carry private data, and secure inference under homomorphic encryption lets a client outsource the computation without revealing the prompt. Existing secure inference systems run a forward pass without consuming a token under encryption, and generating text with them requi...

Halil Ibrahim Kanpak, Didem Unat · 0 citations