TIDAL recovers temporal phase signals from LLM-derived semantics of provisioning metadata to enable complementary CVD placement, reducing overload frequency by 79.1% on production traces.
vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention,
8 Pith papers cite this work, alongside 5 external citations. Polarity classification is still indexing.
8
Pith papers citing it
5
external citations · external index
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
HybridGen achieves 1.41x-3.2x average speedups over six prior KV cache methods for LLM inference by using attention logit parallelism, a feedback-driven scheduler, and semantic-aware KV cache mapping.
OmniPilot combines conformal quantile regression with OOD detection to rank LLM serving configurations on mixed GPUs, reporting 6.2% MAPE throughput prediction and 95% top-1 accuracy on 460 benchmark runs while abstaining on unsupported cases.
KAIROS reduces power by 27% on average (up to 39.8%) for agentic AI inference by using long-lived context to jointly manage GPU frequency, concurrency, and request routing across instances.
Foundry uses template-based CUDA graph context materialization to reduce LLM serving cold-start latency by up to 99% while preserving CUDA graph throughput gains.
Amoeba adaptively adjusts tensor parallelism at runtime for LLM inference services to handle mixed short and long context requests, delivering 1.75x-6.57x throughput gains over prior solutions in real-world trace evaluations.
Festina reduces energy consumption by up to 56% for serverless LLM inference on shared GPUs while keeping TTFT/TBT SLO attainment within 2% of four state-of-the-art baselines.
citing papers explorer
-
TIDAL: Recovering Temporal Phase for Cloud Block Storage Placement from LLM-Derived Semantics
TIDAL recovers temporal phase signals from LLM-derived semantics of provisioning metadata to enable complementary CVD placement, reducing overload frequency by 79.1% on production traces.
-
HybridGen: Efficient LLM Generative Inference via CPU-GPU Hybrid Computing
HybridGen achieves 1.41x-3.2x average speedups over six prior KV cache methods for LLM inference by using attention logit parallelism, a feedback-driven scheduler, and semantic-aware KV cache mapping.
-
OmniPilot: An Uncertainty-Aware LLM Inference Advisor for Heterogeneous GPU Clusters
OmniPilot combines conformal quantile regression with OOD detection to rank LLM serving configurations on mixed GPUs, reporting 6.2% MAPE throughput prediction and 95% top-1 accuracy on 460 benchmark runs while abstaining on unsupported cases.
-
KAIROS: Stateful, Context-Aware Power-Efficient Agentic Inference Serving
KAIROS reduces power by 27% on average (up to 39.8%) for agentic AI inference by using long-lived context to jointly manage GPU frequency, concurrency, and request routing across instances.
-
Foundry: Template-Based CUDA Graph Context Materialization for Fast LLM Serving Cold Start
Foundry uses template-based CUDA graph context materialization to reduce LLM serving cold-start latency by up to 99% while preserving CUDA graph throughput gains.
-
Amoeba: Runtime Tensor Parallel Transformation for LLM Inference Services
Amoeba adaptively adjusts tensor parallelism at runtime for LLM inference services to handle mixed short and long context requests, delivering 1.75x-6.57x throughput gains over prior solutions in real-world trace evaluations.
-
Energy-Aware Scheduling for Serverless LLM Serving on Shared GPUs
Festina reduces energy consumption by up to 56% for serverless LLM inference on shared GPUs while keeping TTFT/TBT SLO attainment within 2% of four state-of-the-art baselines.
- Enforcing Application-Layer Policies in eBPF