Flide: Accelerating Decision Inference with Exact State Forking
Flide rethinks LLM decision serving as a shared state with isolated branches, reporting major speedups while preserving standalone probabilities and reproducibility.
ls ./papers | grep "#LLM inference"
Trending AI research papers from Hugging Face, summarized in plain language: what each paper does, why it matters and where to read more.
2 papers · #LLM inference
Flide rethinks LLM decision serving as a shared state with isolated branches, reporting major speedups while preserving standalone probabilities and reproducibility.
SpecPilot uses cost models, coding agents, and token-level checks to optimize speculative decoding across models, GPUs, and serving regimes without quality loss.