4 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
A load-aware GPU-based dynamic graph pattern matching scheme is proposed to make full use of GPU computing resources and a task overhead prediction model is proposed to guide task allocation to alleviate the load imbalance between multiple GPU devices.
Memory disaggregation provides key-value stores larger memory capacity at low cost. Emerging compute express link (CXL) enables efficient memory disaggregation. It, however, dramatically slows down the system performance as disaggregated memory accesses are considerably slower than local memory accesses. This paper presents Nemo, a near-memory accelerator architecture for CXL-based memory-disaggregated key-value stores. To address the CPU-accelerator latency, Nemo provides a set of new techniques that enable fast task dispatch, cache-conscious task offloading without CPU modifications, and versatile support of custom data types. We evaluate Nemo on the core in-memory index of RocksDB and six widely used in-memory indexing microbenchmarks under YCSB query workloads. Nemo reduces up to 91.8% of slow disaggregated memory accesses, achieves a 2.05 × average speedup over the CPU-only configuration, and accelerates key-value stores by up to 4.5 ×.
LLM agents solve complex tasks by executing multi-step workflows that interleave LLM inference with external tool calls, yet execution efficiency is often the dominant bottleneck in real deployments because LLM-generated workflows are typically chain-structured and inherently sequential, limiting parallelism and underutilizing available compute resources. We propose CoAct, a training-free framework that parallelizes agent workflows by casting execution as an online task allocation problem: CoAct prompts the LLM to generate a pool of discrete subtasks and performs online dispatch by selecting, whenever a worker becomes available, the next task that minimizes an incremental task-contrastive objective, encouraging high similarity among tasks executed on the same path (positive pairs) and low similarity across different paths (negative pairs) to reduce cross-worker interaction and synchronization. CoAct further supports speculative redundancy via selective re-execution to improve robustness and mitigate tail latency. Experiments on tool-augmented agent workloads show that CoAct improves per-step execution efficiency and resource utilization while achieving competitive or superior task accuracy, demonstrating that contrastive online dispatch can expose substantial parallelism in LLM-agent workflows without retraining the underlying model.
LLM agents solve complex tasks by executing multi-step workflows that interleave LLM inference with external tool calls, yet execution efficiency is often the dominant bottleneck in real deployments because LLM-generated workflows are typically chain-structured and inherently sequential, limiting parallelism and underutilizing available compute resources. We propose CoAct, a training-free framework that parallelizes agent workflows by casting execution as an online task allocation problem: CoAct prompts the LLM to generate a pool of discrete subtasks and performs online dispatch by selecting, whenever a worker becomes available, the next task that minimizes an incremental task-contrastive objective, encouraging high similarity among tasks executed on the same path (positive pairs) and low similarity across different paths (negative pairs) to reduce cross-worker interaction and synchronization. CoAct further supports speculative redundancy via selective re-execution to improve robustness and mitigate tail latency. Experiments on tool-augmented agent workloads show that CoAct improves per-step execution efficiency and resource utilization while achieving competitive or superior task accuracy, demonstrating that contrastive online dispatch can expose substantial parallelism in LLM-agent workflows without retraining the underlying model.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
