5 papers
Forge-UGC: FX optimization and register-graph engine for universal graph compiler
Satyam Kumar, Saurabh Jha
We present Forge-UGC (FX Optimization and Register-Graph Engine for Universal Graph Compilation), a four-phase compiler for transformer deployment on heterogeneous accelerator hard…
StreamServe: Adaptive Speculative Flows for Low-Latency Disaggregated LLM Serving
Satyam Kumar, Arpit Singh Gautam, Kailash Talreja +1
Efficient LLM serving must balance throughput and latency across diverse, bursty workloads. We introduce StreamServe, a disaggregated prefill decode serving architecture that combi…
RAMP: Reinforcement Adaptive Mixed Precision Quantization for Efficient On Device LLM Inference
Arpit Singh Gautam, Saurabh Jha
Post training quantization is essential for deploying large language models (LLMs) on resource constrained hardware, yet state of the art methods enforce uniform bit widths across…
The Energy of Falsehood: Detecting Hallucinations via Diffusion Model Likelihoods
Arpit Singh Gautam, Kailash Talreja, Saurabh Jha
Large Language Models (LLMs) frequently hallucinate plausible but incorrect assertions, a vulnerability often missed by uncertainty metrics when models are confidently wrong. We pr…
CogniSQL-R1-Zero: Lightweight Reinforced Reasoning for Efficient SQL Generation
Kushal Gajjar, Harshit Sikchi, Arpit Singh Gautam +2
Translating natural language into SQL (Text-to-SQL) remains a core challenge at the intersection of language understanding and structured data access. Although large language model…