Sieve dynamically schedules MoE experts across GPU and PIM hardware to handle bimodal token distributions, achieving 1.3x to 1.6x gains in throughput and interactivity over static prior PIM systems on three large models.
Title resolution pending
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
years
2026 7representative citing papers
CachePrune enables fine-grained, token-level KV cache reuse across LLM requests by masking sensitive segments, eliminating direct side-channel leakage while cutting TTFT by 4.5x and raising hit rates by 44% versus prior coarse-grained methods.
FlashFPS accelerates FPS via candidate/iteration pruning and inter-layer caching, delivering 5.16x GPU speedup and 2.69x on accelerators with negligible accuracy loss.
PAT adaptively reconfigures tensor parallelism in RLHF generation using predictor-guided decisions and lightweight state updates, cutting generation latency by up to 34.6%.
MTServe achieves up to 3.1x speedup for generative recommendation model serving by using hierarchical caches with host RAM and system optimizations while keeping cache hit ratios above 98.5%.
TOPCELL reformulates standard cell topology optimization as an LLM generative task with GRPO fine-tuning, outperforming base models and matching exhaustive solvers with 85.91x speedup in 2nm/7nm industrial flows.
DeepStack introduces a fast performance model and hierarchical search method for co-optimizing 3D DRAM stacking, interconnects, and distributed scheduling in AI accelerators, delivering up to 9.5x throughput gains over baselines.
citing papers explorer
-
Sieve: Dynamic Expert-Aware PIM Acceleration for Evolving Mixture-of-Experts Models
Sieve dynamically schedules MoE experts across GPU and PIM hardware to handle bimodal token distributions, achieving 1.3x to 1.6x gains in throughput and interactivity over static prior PIM systems on three large models.
-
CachePrune: Privacy-Aware and Fine-Grained KV Cache Sharing for Efficient LLM Inference
CachePrune enables fine-grained, token-level KV cache reuse across LLM requests by masking sensitive segments, eliminating direct side-channel leakage while cutting TTFT by 4.5x and raising hit rates by 44% versus prior coarse-grained methods.
-
FlashFPS: Efficient Farthest Point Sampling for Large-Scale Point Clouds via Pruning and Caching
FlashFPS accelerates FPS via candidate/iteration pruning and inter-layer caching, delivering 5.16x GPU speedup and 2.69x on accelerators with negligible accuracy loss.
-
Accelerating Long-Tail Generation in Synchronous RLHF Training via Adaptive Tensor Parallelism
PAT adaptively reconfigures tensor parallelism in RLHF generation using predictor-guided decisions and lightweight state updates, cutting generation latency by up to 34.6%.
-
MTServe: Efficient Serving for Generative Recommendation Models with Hierarchical Caches
MTServe achieves up to 3.1x speedup for generative recommendation model serving by using hierarchical caches with host RAM and system optimizations while keeping cache hit ratios above 98.5%.
-
TOPCELL: Topology Optimization of Standard Cell via LLMs
TOPCELL reformulates standard cell topology optimization as an LLM generative task with GRPO fine-tuning, outperforming base models and matching exhaustive solvers with 85.91x speedup in 2nm/7nm industrial flows.
-
DeepStack: Scalable and Accurate Design Space Exploration for Distributed 3D-Stacked AI Accelerators
DeepStack introduces a fast performance model and hierarchical search method for co-optimizing 3D DRAM stacking, interconnects, and distributed scheduling in AI accelerators, delivering up to 9.5x throughput gains over baselines.