ASSERT: Adaptive Stochastic Sampling for Robust Diffusion Models on Analog Compute-in-Memory Hardware
Paper • 2609.00955 • Published
Yuannuo Feng
PhD student at Beihang University — efficient LLM inference, speculative decoding, compute-in-memory.
- Homepage: kissmetothemoon.github.io
- GitHub: @Kissmetothemoon
- Google Scholar: profile
Models
- approximate-speculative-decoding — ASD as a
custom_generatemethod for Transformers (5.19.x). Deterministic, bounded-regret acceptance policy for greedy assisted decoding; token-identical to strict verification at budget 0. Usage:
model.generate(..., assistant_model=draft,
custom_generate="ynFeng/approximate-speculative-decoding", trust_remote_code=True,
assistant_asd_budget=2.0, assistant_asd_local_ratio=0.25, assistant_asd_max_mismatches=2)
Papers
- Approximate Speculative Decoding — ASD: training-free bounded-regret verifier for speculative decoding
- ASSERT: Adaptive Stochastic Sampling for Robust Diffusion Models on Analog Compute-in-Memory Hardware — ASP-DAC 2027
- Selective KV Cache Protection for Noise-Resilient LLM Inference on Analog Compute-in-Memory Systems
- ROMER: Expert Replacement and Router Calibration for Robust MoE LLMs on Analog Compute-in-Memory Systems
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Papers for ynFeng/ynFeng
Approximate Speculative Decoding
Paper • 2608.03447 • Published • 1
Selective KV Cache Protection for Noise-Resilient LLM Inference on Analog Compute-In-Memory Systems
Paper • 2607.29076 • Published
ROMER: Expert Replacement and Router Calibration for Robust MoE LLMs on Analog Compute-in-Memory Systems
Paper • 2605.11800 • Published