arXiv subjects

Cyril Y. He

Publications and source records attributed to Cyril Y. He.

3 recordsLinked to original sources

arXiv2026

Scaling LLM Inference Beyond Amdahl`s Limits via Eliminating Non-Scalable Overheads

Deployers of online LLM services usually seek to maximize cluster-wide performance given a fixed number of GPUs. Tensor parallelism (TP) is necessary to fit modern models but scales sub-linearly as the TP degree t grows, due to cross-GPU communication and non-scalable runtime work, as predicted by Amdahl's Law. Conversely, increasing t improves memory efficiency and alleviates KV-cache contention and swapping. We identify and validate an empirical optimal TP degree t_e that balances these effects. We present Albireo, a parallel inference system that raises the attainable t_e by shrinking the non-scalable portion via overlap of scheduling and I/O with compute and sequence-parallel sampling, without changing model architectures. Across models and benchmarks, Albireo achieves up to 1.9x higher throughput, 48% lower latency, 28% higher GPU utilization, and 54% lower energy than vLLM; in production it yields up to 2x higher throughput.

cs.DC↗

arXiv2026

SiDP: Memory-Efficient Data Parallelism for Offline LLM Inference

The rapid adoption of large language models (LLMs) has shifted a substantial portion of inference workloads into throughput-oriented offline regimes, where fully utilizing GPU compute requires large batch sizes. However, existing deployments face a structural tension. Data parallelism (DP) scales throughput well but replicates model weights, leaving limited GPU memory for key-value (KV) cache and constraining batch size. Model parallelism reduces per-device weights, but requires fine-grained synchronization that erodes DP's independence and scheduling flexibility. We present SiDP, a memory-efficient data-parallel paradigm for offline LLM inference that treats weights as a bandwidth-backed shared resource inside a DP group. Instead of storing the full model on every GPU, SiDP organizes weights as a distributed pool: each layer is owned by a single GPU, and other replicas access its weights on demand via two complementary execution modes: a Weight-as-a-Service (WaS) mode that streams remote weights over NVLink into a small cache in the large-batch regime, and a Compute-as-a-Service (CaS) mode that ships activations to owners in the small-batch tail. Evaluated on NVIDIA H20, H200, and B200 GPUs with Qwen3-32B, Qwen2.5-72B, and Llama-3.1-70B, SiDP increases usable KV capacity by up to 1.8x under the same configurations, and converts this into up to 1.5x higher end-to-end throughput over baselines (vLLM) for offline workloads.

cs.DC↗

arXiv2026

ConfSpec: Efficient Step-Level Speculative Reasoning via Confidence-Gated Verification

Chain-of-Thought reasoning significantly improves the performance of large language models on complex tasks, but incurs high inference latency due to long generation traces. Step-level speculative reasoning aims to mitigate this cost, yet existing approaches face a long-standing trade-off among accuracy, inference speed, and resource efficiency. We propose ConfSpec, a confidence-gated cascaded verification framework that resolves this trade-off. Our key insight is an asymmetry between generation and verification: while generating a correct reasoning step requires substantial model capacity, step-level verification is a constrained discriminative task for which small draft models are well-calibrated within their competence range, enabling high-confidence draft decisions to be accepted directly while selectively escalating uncertain cases to the large target model. Evaluation across diverse workloads shows that ConfSpec achieves up to 2.24$\times$ end-to-end speedups while matching target-model accuracy. Our method requires no external judge models and is orthogonal to token-level speculative decoding, enabling further multiplicative acceleration.

cs.CL↗