2 papers
cs.AI2026
Few Bits, One Law: Toward W2A4KV2
Kai Yi, Tarek Elgamal, Sruthikesh Surineni +3
Extreme low-bit LLM compression is most challenging when weights, activations, and KV caches are quantized together: their distributions differ, and quantization errors interact th…
cs.LG2026
MoE-Spec: Expert Budgeting for Efficient Speculative Decoding
Bradley McDanel, Steven Li, Sruthikesh Surineni +1
Speculative decoding accelerates Large Language Model (LLM) inference by verifying multiple drafted tokens in parallel. However, for Mixture-of-Experts (MoE) models, this paralleli…