5 papers
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…
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…
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…
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…
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…