LLMVisor is presented, a roofline-guided latency attribution model that captures the memory-bound and compute-bound phases via a concise piecewise-linear form over features proportional to FLOPs and memory I/O traffic and runs efficiently at microsecond scale.
Abstract
As LLM inference shifts to multi-tenant GPU clusters, co-batching improves throughput but obscures per-tenant usage and limits control. Enabling fractional sharing of the inference engine requires a real-time, per-request attribution primitive that is accurate and light enough to run inside the scheduling loop. We present LLMVisor, a roofline-guided latency attribution model that captures the memory-bound and compute-bound phases via a concise piecewise-linear form over features proportional to FLOPs and memory I/O traffic. LLMVisor decomposes batch latency into additive, per-request shares and runs efficiently at microsecond scale. We evaluate LLMVisor across Llama 3.1-8B and Qwen 2.5-14B/32B on A100/H100 GPUs under varying tensor parallelism and workload mixes. Compared to a token-count baseline, LLMVisor attains near-perfect R-squared and reduces relative error by up to 2.5x and 3.3x at p90 and p99, respectively, for prefill, and by up to 3.5x and 4.4x for decode, despite batching variability and sequence divergence.
Or OrionInfer, an adaptive LLM serving system that aligns inference strategies with real-time demand and introduces three key techniques: runtime switching between data parallelism and tensor parallelism with negligible overhead, an efficient inference pipeline that preserves batching efficiency during parallelism transitions, and live-migration-based load balancing to alleviate memory pressure and improve resource utilization.
Jingqi Feng, Guang Yang, Yukai Huang et al.· Proceedings of the 32nd ACM...· 0 citations
Large language model (LLM) inference serving is priced by tokens, but GPU energy is consumed over inference windows. This accounting mismatch makes token-normalized metrics incomplete, since average output-token energy can decrease even when total request energy increases. We characterize this behavior with a decomposed energy model: a fixed one-time prefill with a fixed generation setup cost, while each output-token generation step adds marginal step energy. We evaluate this LLM inference energy model on NVIDIA H100 and H200 GPUs across dense and mixture-of-experts (MoE) models, reporting both request energy and token energy as functions of model type (M), phase (P), batch size (B), context length (C), and output length (N). For Llama-3.2-1B on H200 at batch-16 and context-4K, increasing output length from 10 to 512 tokens reduces token energy from 7.46 to 0.72 J/token while total batched inference-window energy increases from 1.19 to 5.93 kJ. Batching also reduces token energy, but the gain is context-bounded: at 10 output tokens, the batch-16 to batch-1 gain falls from 6.31x at context-512 to 1.17x at context-4K. MoE models amplify this effect: sparse routing and fragmented expert execution increase fixed energy at low concurrency, while batching spreads that energy across more generated tokens and substantially narrows the dense-vs.-MoE token-energy gap. These results show that energy-aware serving should jointly optimize both request energy and token energy, rather than only reducing per-token energy cost.
P. Vellaisamy, Vanessa Lam, Shawn Blanton et al.· 0 citations
The rise of reasoning models and agentic systems has made LLM token-generation latency a key bottleneck. Unlike chatbots, whose latency gains saturate at human reading speed, these systems generate intermediate reasoning tokens not consumed by humans. Thus, per-token latency directly determines end-to-end response time. Low-latency inference uses minimal batching, making token generation bandwidth-bound. Tensor Parallelism addresses this by sharding model weights across GPUs and loading them in parallel. However, scaling to more GPUs introduces All-Reduce overheads that grow with GPU count. Removing All-Reduce improves token throughput by 43% for Llama-3.1-8B on 8 H200 GPUs. We propose Synchronization-Free All-Reduce (SiFAR), which reduces synchronization overhead during low-latency inference. Existing oneshot and twoshot algorithms incur overheads from barriers before and after communication. First, we find that the bottom barrier in oneshot enforces a WAW dependency and eliminate it by co-designing communication and model execution to enable dual buffering. However, oneshot scales poorly with GPU count. Twoshot performs better at higher TP degrees but incurs an unavoidable bottom barrier. To overcome this, we leverage in-switch reduction in modern switches. We propose redundant pull, where each GPU reduces the full All-Reduce payload at the switch. This improves oneshot scalability while retaining its no-bottom-barrier advantage. Finally, to reduce top-barrier overhead, we observe that each decode step issues multiple All-Reduce operations, keeping GPUs tightly synchronized after the first. We therefore propose speculative reduction, which initiates data transfer before the top barrier and ensures correctness via lightweight validation. SiFAR reduces All-Reduce latency by up to 52% and improves end-to-end throughput by 18.6% for Llama-3.1-8B and 13.1% for Qwen3.5-397B-17B at TP=8.
Hritvik Taneja, A. Saxena, Abhishek Revinipati et al.· 1 citation
MaverIQ is an intent-based LLM inference serving system that automatically maps user intents to deployment configurations while minimizing operational cost for the provider and reduces profiling overheads by 7-15× compared to state-of-the-art baselines.
Dimitrios Liakopoulos, Prasoon Sinha, Tianrui Hu et al.· ACM SIGOPS Operating Systems...· 0 citations
A split-phase heterogeneous deployment strategy is proposed, and key optimization paths, including operator ecosystem completion and deep operator fusion, are identified.
SemaCredit is presented, a receiver controller that admits each remote-memory operation against a vector of target-resource demands and returns each component when its corresponding HBM, Atomic, or response stage completes, reducing small-operation P99 latency by 52.4% under Atomic contention and 10.2% under response incast.
Fan Yang, Jiaqi Liu, Tao Jiang et al.· 0 citations