Publications (11)
NGEMM: Optimizing GEMM for Deep Learning via Compiler-based Techniques
Wenlei Bao, Li-Wen Chang, Yang Chen +4
Quantization has emerged to be an effective way to significantly boost the performance of deep neural networks (DNNs) by utilizing low-bit computations. Despite having lower numeri…
Comet: Fine-grained Computation-communication Overlapping for Mixture-of-Experts
Shulai Zhang, Ningxin Zheng, Haibin Lin +9
Mixture-of-experts (MoE) has been extensively employed to scale large language models to trillion-plus parameters while maintaining a fixed computational cost. The development of l…
DITRON: Distributed Multi-level Tiling Compiler for Parallel Tensor Programs
Size Zheng, Xuegui Zheng, Hanshi Sun +16
The scaling of large language models (LLMs) is currently bottlenecked by the rigidity of distributed programming. While high-performance libraries like CuBLAS and NCCL provide opti…
Optimizing Long-context LLM Serving via Fine-grained Sequence Parallelism
Cong Li, Yuzhe Yang, Xuegui Zheng +7
With the advancement of large language models (LLMs), their context windows have rapidly expanded. To meet diverse demands from varying-length requests in online services, existing…
MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism
Ruidong Zhu, Ziheng Jiang, Chao Jin +17
Mixture-of-Experts (MoE) showcases tremendous potential to scale large language models (LLMs) with enhanced performance and reduced computational complexity. However, its sparsely…
FLUX: Fast Software-based Communication Overlap On GPUs Through Kernel Fusion
Li-Wen Chang, Wenlei Bao, Qi Hou +10
Large deep learning models have demonstrated strong ability to solve many tasks across a wide range of applications. Those large models typically require training and inference to…
veScale: Consistent and Efficient Tensor Programming with Eager-Mode SPMD
Youjie Li, Cheng Wan, Zhiqi Lin +10
Large Language Models (LLMs) have scaled rapidly in size and complexity, requiring increasingly intricate parallelism for distributed training, such as 3D parallelism. This sophist…
TileLink: Generating Efficient Compute-Communication Overlapping Kernels using Tile-Centric Primitives
Size Zheng, Jin Fang, Xuegui Zheng +9
Large deep learning models have achieved state-of-the-art performance in a wide range of tasks. These models often necessitate distributed systems for efficient training and infere…
Triton-distributed: Programming Overlapping Kernels on Distributed AI Systems with the Triton Compiler
Size Zheng, Wenlei Bao, Qi Hou +19
In this report, we propose Triton-distributed, an extension of existing Triton compiler, to overcome the programming challenges in distributed AI systems. Triton-distributed is the…
ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference
Hanshi Sun, Li-Wen Chang, Wenlei Bao +6
With the widespread deployment of long-context large language models (LLMs), there has been a growing demand for efficient support of high-throughput inference. However, as the key…
R-KV: Redundancy-aware KV Cache Compression for Reasoning Models
Zefan Cai, Wen Xiao, Hanshi Sun +11
Reasoning models have demonstrated impressive performance in self-reflection and chain-of-thought reasoning. However, they often produce excessively long outputs, leading to prohib…