Author

Anshu Bansal

h-index 0 View on Semantic Scholar

We have 1 of 1 papers

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

More GPUs or a Smaller Cache? Tensor Parallelism versus KV Compression for Memory-Bound LLM Serving

Tensor parallelism is the only lever that improves latency (compression makes per-token latency worse), while compression is the only lever that multiplies capacity per dollar (16.5x, against 1.21x for an eightfold spend on GPUs).

Srikanta Datta Tumkur, Mehar Simhadri, Anshu Bansal et al. · 0 citations