As machine learning models scale in size and complexity, their computational requirements become a significant barrier. Mixture-of-Experts (MoE) models alleviate this issue by selectively activating relevant experts. Despite this, MoE models are hindered by high communication overhead from all-to-all operations, low GPU utilization, and complications from heterogeneous GPU environments. This paper presents Comet, which optimizes both model deployment and all-to-all communication scheduling to address these challenges in MoE inference. Comet achieves minimal communication times by strategically ordering token transmissions in all-to-all communications. It improves GPU utilization by colocating experts from different models on the same device, avoiding the limitations of all-to-all communication. We analyze Comet’s optimization strategies theoretically across four common GPU cluster settings: exclusive vs. colocated models on GPUs, and homogeneous vs. heterogeneous GPUs. Comet provides optimal solutions for three cases, and for the remaining NP-hard scenario, it offers a polynomial-time sub-optimal solution with only a 1.09× degradation from the optimal, as shown in the simulation results. Comet is the first approach to minimize MoE inference time via optimal model deployment and communication scheduling across various scenarios. Evaluations demonstrate that Comet significantly accelerates inference, achieving speedups of up to 2.63× in homogeneous clusters and 2.91× in heterogeneous environments. Moreover, Comet enhances GPU utilization by up to 2.38× compared to existing methods.

Recent advances in inference-time compute have significantly improved performance on complex tasks by generating long chains of thought (CoTs) using Large Reasoning Models (LRMs). However, this improved accuracy comes at the cost of high inference latency due to the length of generated reasoning sequences and the autoregressive nature of decoding. Our key insight in tackling these overheads is that LRM inference, and the reasoning that it embeds, is highly tolerant of approximations: complex tasks are typically broken down into simpler steps, each of which brings utility based on the semantic insight it provides for downstream steps rather than the exact tokens it generates. Accordingly, we introduce SpecReason, a system that automatically accelerates LRM inference by using a lightweight model to (speculatively) carry out simpler intermediate reasoning steps and reserving the costly base model only to efficiently assess (and potentially correct) the speculated outputs. Importantly, SpecReason's focus on exploiting the semantic flexibility of thinking tokens in preserving final-answer accuracy is complementary to prior speculation techniques, most notably speculative decoding, which demands token-level equivalence at each step. Across a variety of cross-domain reasoning benchmarks, SpecReason achieves 1.4-3.0$\times$ speedup over vanilla LRM inference while improving accuracy by 0.4-9.0%. Compared to speculative decoding without SpecReason, their combination yields an additional 8.8-58.0% latency reduction. We open-source SpecReason at \url{https://anonymous.4open.science/r/specreason/}.

RAG (Retrieval Augmented Generation) allows LLMs (large language models) to generate better responses with external knowledge, but using more external knowledge causes higher response delay. Prior work focuses either on reducing the response delay (e.g., better scheduling of RAG queries) or on maximizing quality (e.g., tuning the RAG workflow), but they fall short in systematically balancing the tradeoff between the delay and quality of RAG responses. To balance both quality and response delay, this paper presents METIS, the first RAG system that jointly schedules queries and adapts the key RAG configurations of each query, such as the number of retrieved text chunks and synthesis methods. Using four popular RAG-QA datasets, we show that compared to the state-of-the-art RAG optimization schemes, METIS reduces the generation latency by 1.64 – 2.54× without sacrificing generation quality.

Machine learning (ML) inference platforms are tasked with balancing two competing goals: ensuring high throughput given many requests, and delivering low-latency responses to support interactive applications. Unfortunately, existing platform knobs (e.g., batch sizes) fail to ease this fundamental tension, and instead only enable users to harshly trade off one property for the other. This paper explores an alternate strategy to taming throughput-latency tradeoffs by changing the granularity at which inference is performed. We present Apparate, a system that automatically applies and manages early exits (EEs) in ML models, whereby certain inputs can exit with results at intermediate layers. To cope with the time-varying overhead and accuracy challenges that EEs bring, Apparate repurposes exits to provide continual feedback that powers several novel runtime monitoring and adaptation strategies. Apparate lowers median response latencies by 40.5--91.5% and 10.0--24.2% for diverse CV and NLP classification workloads, and median time-per-token latencies by 22.6--77.9% for generative scenarios, without affecting throughputs or violating tight accuracy constraints.

Machine learning inference platforms continue to face high request rates and strict latency constraints. Existing solutions largely focus on compressing models to substantially lower compute costs (and time) with mild accuracy degradations. This paper explores an alternate (but complementary) technique that trades off accuracy and resource costs on a perinput granularity: early exit models, which selectively allow certain inputs to exit a model from an intermediate layer. Though intuitive, early exits face fundamental deployment challenges, largely owing to the effects that exiting inputs have on batch size (and resource utilization) throughout model execution. We present E3, the first system that makes early exit models practical for realistic inference deployments. Our key insight is to split and replicate blocks of layers in models in a manner that maintains a constant batch size throughout execution, all the while accounting for resource requirements and communication overheads. Evaluations with NLP and vision models show that E3 can deliver up to 1.74× improvement in goodput (for a fixed cost) or 1.78× reduction in cost (for a fixed goodput). Additionally, E3's goodput wins generalize to autoregressive LLMs (2.8--3.8×) and compressed models (1.67×).

This paper discusses why flow scheduling does not apply to distributed deep learning training and presents EchelonFlow, the first network abstraction to bridge the gap. EchelonFlow deviates from the common belief that semantically related flows should finish at the same time. We reached the key observation, after extensive workflow analysis of diverse training paradigms, that distributed training jobs observe strict computation patterns, which may consume data at different times. We devise a generic method to model the drastically different computation patterns across training paradigms, and formulate EchelonFlow to regulate flow finish times accordingly. Case studies of mainstream training paradigms under EchelonFlow demonstrate the expressiveness of the abstraction, and our system sketch suggests the feasibility of an EchelonFlow scheduling system.