Power capping is illusory in LLM decode as memory-bound operation leaves power headroom untouched on 700 W GPUs, while SM clock locking saves up to 32% energy and three DVFS classes appear across attention types.
hub
Gulavani, and Ramachandran Ramjee
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
hub tools
citation-role summary
baseline 1
citation-polarity summary
roles
baseline 1polarities
baseline 1representative citing papers
Kairos improves SLO attainment and throughput in LLM serving by adapting to request length imbalance with priority scheduling and adaptive batching.
A training-inference consistent segmented execution framework for long-context LLMs matches full-context performance with substantially lower peak memory at very long lengths.
SPECTRE achieves up to 2.28x speedup for large-model LLM serving by running speculative draft generation and target verification in parallel using idle tail-model services.
ZeRO-Prefill achieves 1.35-1.59x higher throughput for MoE prefill serving by replacing per-layer activation AllToAll with overlapped asynchronous weight AllGather and prefix-aware routing.
SPIN co-designs sparse attention with hierarchical memory to achieve 1.66-5.66x higher throughput, 7-9x lower TTFT, and up to 58% lower TPOT than vLLM and original sparse implementations.
AMMA is a memory-centric multi-chiplet architecture using HBM-PNM cubes, custom logic dies, hybrid parallelism, and reordered collectives that delivers 15.5X lower attention latency and 6.9X lower energy than NVIDIA H100 for 1M context serving.
Salca is a new ASIC accelerator that achieves 3.82× speedup and 74.19× energy efficiency over A100 for long-context attention via dual-compression dynamic sparse attention and pipelined hardware.
NPUMoE accelerates MoE LLM inference on Apple Silicon NPUs via offline-calibrated static expert tiers, grouped execution, and load-aware graph residency, delivering 1.32x-5.55x lower latency and 1.81x-7.37x better energy efficiency.
MARS coordinates heterogeneous GPU-CPU resources for agentic LLM workloads via decoupled admission control and agent-centric KV cache management, delivering up to 5.94x lower latency and 1.87x faster task completion.
A flow-control framework for LLM inference derives necessary and sufficient stability conditions and experimentally improves throughput, latency, and KV cache stability over common baselines.
Valve jointly bounds preemption latency and rate for online-offline LLM colocation on GPUs, delivering 34.6% higher cluster utilization and a 2,170-GPU saving in a production deployment of 8,054 GPUs with under 5% TTFT and 2% TPOT impact.
HybridFlow combines single- and multi-controller paradigms with a 3D-HybridEngine to deliver 1.53x to 20.57x higher throughput for various RLHF algorithms compared to prior systems.
PipeMax integrates pipeline parallelism with offloading to achieve up to 2.51x higher throughput than vLLM for offline LLM inference on commodity 8-GPU servers.
EdgeFM is an agent-driven framework that strips non-essential features from VLMs and packages reusable optimized kernels, achieving up to 1.49x speedup over TensorRT-Edge-LLM on NVIDIA Orin while enabling first end-to-end deployment on Horizon Journey hardware.
citing papers explorer
-
The Illusion of Power Capping in LLM Decode: A Phase-Aware Energy Characterisation Across Attention Architectures
Power capping is illusory in LLM decode as memory-bound operation leaves power headroom untouched on 700 W GPUs, while SM clock locking saves up to 32% energy and three DVFS classes appear across attention types.
-
Taming Request Imbalance: SLO-Aware Scheduling for Disaggregated LLM Inference
Kairos improves SLO attainment and throughput in LLM serving by adapting to request length imbalance with priority scheduling and adaptive batching.
-
Training-Inference Consistent Segmented Execution for Long-Context LLMs
A training-inference consistent segmented execution framework for long-context LLMs matches full-context performance with substantially lower peak memory at very long lengths.
-
SPECTRE: Hybrid Ordinary-Parallel Speculative Serving for Resource-Efficient LLM Inference
SPECTRE achieves up to 2.28x speedup for large-model LLM serving by running speculative draft generation and target verification in parallel using idle tail-model services.
-
ZeRO-Prefill: Zero Redundancy Overheads in MoE Prefill Serving
ZeRO-Prefill achieves 1.35-1.59x higher throughput for MoE prefill serving by replacing per-layer activation AllToAll with overlapped asynchronous weight AllGather and prefix-aware routing.
-
Unifying Sparse Attention with Hierarchical Memory for Scalable Long-Context LLM Serving
SPIN co-designs sparse attention with hierarchical memory to achieve 1.66-5.66x higher throughput, 7-9x lower TTFT, and up to 58% lower TPOT than vLLM and original sparse implementations.
-
AMMA: A Multi-Chiplet Memory-Centric Architecture for Low-Latency 1M Context Attention Serving
AMMA is a memory-centric multi-chiplet architecture using HBM-PNM cubes, custom logic dies, hybrid parallelism, and reordered collectives that delivers 15.5X lower attention latency and 6.9X lower energy than NVIDIA H100 for 1M context serving.
-
Salca: A Sparsity-Aware Hardware Accelerator for Efficient Long-Context Attention Decoding
Salca is a new ASIC accelerator that achieves 3.82× speedup and 74.19× energy efficiency over A100 for long-context attention via dual-compression dynamic sparse attention and pipelined hardware.
-
Efficient Mixture-of-Experts LLM Inference with Apple Silicon NPUs
NPUMoE accelerates MoE LLM inference on Apple Silicon NPUs via offline-calibrated static expert tiers, grouped execution, and load-aware graph residency, delivering 1.32x-5.55x lower latency and 1.81x-7.37x better energy efficiency.
-
MARS: Efficient, Adaptive Co-Scheduling for Heterogeneous Agentic Systems
MARS coordinates heterogeneous GPU-CPU resources for agentic LLM workloads via decoupled admission control and agent-centric KV cache management, delivering up to 5.94x lower latency and 1.87x faster task completion.
-
Flow-Controlled Scheduling for LLM Inference with Provable Stability Guarantees
A flow-control framework for LLM inference derives necessary and sufficient stability conditions and experimentally improves throughput, latency, and KV cache stability over common baselines.
-
Valve: Production Online-Offline Inference Colocation with Jointly-Bounded Preemption Latency and Rate
Valve jointly bounds preemption latency and rate for online-offline LLM colocation on GPUs, delivering 34.6% higher cluster utilization and a 2,170-GPU saving in a production deployment of 8,054 GPUs with under 5% TTFT and 2% TPOT impact.
-
HybridFlow: A Flexible and Efficient RLHF Framework
HybridFlow combines single- and multi-controller paradigms with a 3D-HybridEngine to deliver 1.53x to 20.57x higher throughput for various RLHF algorithms compared to prior systems.
-
PipeMax: Enhancing Offline LLM Inference on Commodity GPU Servers
PipeMax integrates pipeline parallelism with offloading to achieve up to 2.51x higher throughput than vLLM for offline LLM inference on commodity 8-GPU servers.
-
EdgeFM: Efficient Edge Inference for Vision-Language Models
EdgeFM is an agent-driven framework that strips non-essential features from VLMs and packages reusable optimized kernels, achieving up to 1.49x speedup over TensorRT-Edge-LLM on NVIDIA Orin while enabling first end-to-end deployment on Horizon Journey hardware.
- RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference