Author

Amir Ziashahabi

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 Aug 2026

Spend Bits Where Queries Look: KV Cache Vector Quantization with Attention-Preserving Transforms

Long-context LLM decoding reads the key-value (KV) cache at every step. Loading it takes longer than computing attention over it, so throughput is bandwidth-bound. Hence, reducing the cache size can raise both decoding speed and serving capacity. The challenge is to reduce cache size while preserving the attention prod...

Samuel Fernández-Menduiña, Amir Ziashahabi, Eduardo Pavez et al. · 0 citations

#machine learning Preprint Sep 2026

ASPIRE: Asynchronous Batched Self-Speculative Decoding for Long-Context LLM Inference

Long-context LLM inference is bottlenecked by attention, whose repeated KV-cache reads make decoding memory-bound. Self-speculative decoding alleviates this by drafting tokens with sparse attention and verifying them with full attention, but existing batched methods remain synchronized: all requests in a batch share a...

Amir Ziashahabi, Hossein Entezari Zarch, Lei Gao et al. · 0 citations