Chunqiang Tang
Publications
ROCS: Request-Oriented Compute Sharing for Efficient Large-Scale Recommendation
Modern recommendation models gain prediction quality by scaling feature-interaction and sequence modules, but production cost constraints cap how far systems can scale. In this work, we propose Request-Oriented Compute Sharing (ROCS), a modeling and inference paradigm that exploits a unique property of recommendation inference: each user request is evaluated against many candidates, while request-side features are shared across candidates. ROCS defers request-candidate interactions as late as possible, isolates candidate-dependent representations, and evaluates substantial portions of the model once per request rather than once per candidate, significantly improving inference efficiency while maintaining or improving prediction quality. To realize this paradigm, we develop Generalized Layer Masking (GLM) to enforce candidate isolation in feature-interaction architectures, and Deep Cross Attention (DCA) to extend request-oriented sharing to sequence architectures. To support efficient GPU deployment, we co-design In-Kernel Broadcast Optimization (IKBO) that significantly accelerates ROCS model execution. Experiments on public benchmarks show that ROCS consistently improves the quality-efficiency tradeoff across recommendation backbones. On production-scale workloads, ROCS achieves up to a 3x QPS improvement on retrieval models without quality degradation and a 0.5% relative LogLoss improvement with a 50% QPS gain on a short-form video ranking model. ROCS has been deployed across large-scale recommendation systems spanning ads and organic surfaces, retrieval and ranking stages, and more than two orders of magnitude in inference complexity, delivering significant online gains at reduced infrastructure cost.
Scaling Multi-Node Mixture-of-Experts Inference Using Expert Activation Patterns
Most recent state-of-the-art (SOTA) large language models (LLMs) use Mixture-of-Experts (MoE) architectures to scale model capacity without proportional per-token compute, enabling higher-quality outputs at manageable serving costs. However, MoE inference at scale is fundamentally bottlenecked by expert load imbalance and inefficient token routing, especially in multi-node deployments where tokens are not guaranteed to be routed to local experts, resulting in significant inter-node all-to-all communication overhead. To systematically characterize these challenges, we profile SOTA open-source MoE models, including Llama 4 Maverick, DeepSeek V3-671B, and Qwen3-230B-A22B, on various datasets and collected over 100k real expert activation traces. Upon studying the expert activation patterns, we uncover various persistent properties across all the frontier MoE models: variable expert load imbalance, domain-specific expert activation where expert popularity shifts across task families (code, math, chat, general), and a strong correlation between prefill and decode expert activations. Motivated by these findings, we propose workload-aware micro-batch grouping and an expert placement strategy to maximize token locality to the destination expert, thereby reducing inter-node communication. Across models and datasets, these optimizations help reduce all2all communication data up to 20, resulting in lower MoE decode latency and better accelerator utilization.
Training LLMs with Fault Tolerant HSDP on 100,000 GPUs
Large-scale training systems typically use synchronous training, requiring all GPUs to be healthy simultaneously. In our experience training on O(100K) GPUs, synchronous training results in a low efficiency due to frequent failures and long recovery time. To address this problem, we propose a novel training paradigm, Fault Tolerant Hybrid-Shared Data Parallelism (FT-HSDP). FT-HSDP uses data parallel replicas as units of fault tolerance. When failures occur, only a single data-parallel replica containing the failed GPU or server is taken offline and restarted, while the other replicas continue training. To realize this idea at scale, FT-HSDP incorporates several techniques: 1) We introduce a Fault Tolerant All Reduce (FTAR) protocol for gradient exchange across data parallel replicas. FTAR relies on the CPU to drive the complex control logic for tasks like adding or removing participants dynamically, and relies on GPU to perform data transfer for best performance. 2) We introduce a non-blocking catch-up protocol, allowing a recovering replica to join training with minimal stall. Compared with fully synchronous training at O(100K) GPUs, FT-HSDP can reduce the stall time due to failure recovery from 10 minutes to 3 minutes, increasing effective training time from 44\% to 80\%. We further demonstrate that FT-HSDP's asynchronous recovery does not bring any meaning degradation to the accuracy of the result model.