1 citations · 1 across the 5 of their papers we have counts for
6 papers
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
DeepSeek-AI, :, Anyi Xu +585
The widespread adoption of long-horizon agents has made model workloads increasingly input-heavy. Although prior work has substantially reduced the cost of long-context computation…
A Few GPUs, A Whole Lotta Scale: Faithful LLM Training Emulation with PrismLLM
Shaoke Xi, ChonLam Lao, Boyi Jia +11
Large language model (LLM) training today runs on clusters spanning thousands of GPUs. While this scale enables rapid model advances, developing, debugging, and performance-tuning…
Accelerating Compound LLM Training Workloads with Maestro
Xiulong Yuan, Hongqing Chen, Jiaxuan Peng +16
Compound LLM training workloads-such as knowledge distillation and multimodal LLM (MLLM) training-are gaining prominence. These typically comprise heterogeneous components differin…
TrainMover: An Interruption-Resilient Runtime for ML Training
ChonLam Lao, Jiaqi Gao, Jiamin Cao +13
Large-scale ML training jobs are frequently interrupted by hardware and software anomalies, failures, and management events. Existing solutions like checkpoint-restart or runtime r…
Accelerating Stateful Network Applications with Performance Prediction on SoC SmartNICs
Shaoke Xi, Jiaqi Gao, Mengqi Liu +7
Offloading stateful network functions to multi-threaded SoC SmartNICs promises significant performance and cost benefits. However, realizing this potential is hindered by two funda…
EdgeSight: Enabling Modeless and Cost-Efficient Inference at the Edge
ChonLam Lao, Jiaqi Gao, Ganesh Ananthanarayanan +2
Traditional ML inference is evolving toward modeless inference, which abstracts the complexity of model selection from users, allowing the system to automatically choose the most a…