Related papers: ChunkFlow: Communication-Aware Chunked Prefetching…

Efficient LLM inference on resource-constrained devices presents significant challenges in compute and memory utilization. Due to limited GPU memory, existing systems offload model weights to CPU memory, incurring substantial I/O overhead…

This paper provides an in-depth characterization of GPU-accelerated systems, to understand the interplay between overlapping computation and communication which is commonly employed in distributed training settings. Due to the large size of…

Diffusion models demonstrate outstanding performance in image generation, but their multi-step inference mechanism requires immense computational cost. Previous works accelerate inference by leveraging layer or token cache techniques to…

Diffusion Transformers (DiTs) are increasingly adopted in scientific computing, yet growing model sizes and resolutions make distributed multi-GPU inference essential. Ulysses sequence parallelism scales DiT inference but introduces…

Diffusion Transformers (DiT) are powerful generative models but remain computationally intensive due to their iterative structure and deep transformer stacks. To alleviate this inefficiency, we propose \textbf{FastCache}, a…

As multimodal and AI-driven services exchange hundreds of megabytes per request, existing IPC runtimes spend a growing share of CPU cycles on memory copies. Although both hardware and software mechanisms are exploring memory offloading,…

Large-scale AI model training divides work across thousands of GPUs, then synchronizes gradients across them at each step. This incurs a significant network burden that only centralized, monolithic clusters can support, driving up…

LLM training at the scale of tens of thousands of GPUs now spans multiple datacenters (DC), making cross-DC collectives over long-haul links unavoidable. A critical and overlooked bottleneck arises when these collectives collide with…

Transformers and LLMs have seen rapid adoption in all domains. Their sizes have exploded to hundreds of billions of parameters and keep increasing. Under these circumstances, the training of transformers is slow and often takes in the order…

The continued growth of the computational capability of throughput processors has made throughput processors the platform of choice for a wide variety of high performance computing applications. Graphics Processing Units (GPUs) are a prime…

Transformer architectures, particularly Diffusion Transformers (DiTs), have become widely used in diffusion and flow-matching models due to their strong performance compared to convolutional UNets. However, the isotropic design of DiTs…

Graph Neural Networks (GNNs) play a crucial role in various fields. However, most existing deep graph learning frameworks assume pre-stored static graphs and do not support training on graph streams. In contrast, many real-world graphs are…

Communication scheduling aims to reduce communication bottlenecks in data parallel training (DP) by maximizing the overlap between computation and communication. However, existing schemes fall short due to three main issues: (1) hard data…

Distributing Transformer inference across embedded edge devices can alleviate individual memory and compute constraints, yet practical benefits on real hardware remain unclear: prior work relies largely on simulations that overlook…

The growing adoption of generative AI in real-world applications has exposed a critical bottleneck in the computational demands of diffusion-based text-to-image models. In this work, we propose KDC-Diff, a novel and scalable generative…

In GPU-accelerated data analytics, the overhead of data transfer from CPU to GPU becomes a performance bottleneck when the data scales beyond GPU memory capacity due to the limited PCIe bandwidth. Data compression has come to rescue for…

Diffusion Transformers rely on static patchify tokenization, assigning the same token budget to smooth backgrounds, detailed object regions, noisy early timesteps, and late-stage refinements. We introduce the Dynamic Chunking Diffusion…

Diffusion model deployment has been suffering from high energy consumption and inference latency despite its superior performance in visual generation tasks. Dynamic voltage and frequency scaling (DVFS) offers a promising solution to…

The expansion of large language models is increasingly limited by the constrained memory capacity of modern GPUs. To mitigate this, Mixture-of-Experts (MoE) architectures activate only a small portion of parameters during inference,…

KV cache restoration has emerged as a dominant bottleneck in serving long-context LLM workloads, including multi-turn conversations, retrieval-augmented generation, and agentic pipelines. Existing approaches treat restoration as a…