activity
20242026
collaborators

5 papers

cs.OS2026

TClone: Low-Latency Forking of Live GUI Environments for Computer-Use Agents

Yutong Huang, Vikranth Srivatsa, Alex Asch +2

Computer-use agents increasingly operate inside live personal workspaces, where their actions can modify files, applications, GUI state, credentials, and authenticated sessions. Th…

cs.DC2026

Nitsum: Serving Tiered LLM Requests with Adaptive Tensor Parallelism

Vikranth Srivatsa, Zijian He, Pu Guo +2

LLM serving is increasingly multi-tenant: the same deployment must handle latency-critical interactive requests and more relaxed background workloads under a fixed GPU budget. This…

cs.LG2025

Beat the long tail: Distribution-Aware Speculative Decoding for RL Training

Zelei Shao, Vikranth Srivatsa, Sanjana Srivastava +12

Reinforcement learning(RL) post-training has become essential for aligning large language models (LLMs), yet its efficiency is increasingly constrained by the rollout phase, where…

cs.LG2025

Cognify: Supercharging Gen-AI Workflows With Hierarchical Autotuning

Zijian He, Reyna Abhyankar, Vikranth Srivatsa +1

Today's gen-AI workflows that involve multiple ML model calls, tool/API calls, data retrieval, or generic code execution are often tuned manually in an ad-hoc way that is both time…

cs.DC2024

Preble: Efficient Distributed Prompt Scheduling for LLM Serving

Vikranth Srivatsa, Zijian He, Reyna Abhyankar +2

Prompts to large language models (LLMs) have evolved beyond simple user questions. For LLMs to solve complex problems, today's practices are to include domain-specific instructions…