3 papers
cs.LG2026
LLM-42: Enabling Determinism in LLM Inference with Verified Speculation
Raja Gond, Aditya K Kamath, Ramachandran Ramjee +1
In LLM inference, the same prompt may yield different outputs across different runs. At the system level, this non-determinism arises from floating-point non-associativity combined…
cs.DC2025
TokenWeave: Efficient Compute-Communication Overlap for Distributed LLM Inference
Raja Gond, Nipun Kwatra, Ramachandran Ramjee
Distributed inference of large language models (LLMs) using tensor parallelism can introduce communication overheads of % even over GPUs connected via NVLink, a high-speed GPU…
cs.DC2024
emucxl: an emulation framework for CXL-based disaggregated memory applications
Raja Gond, Purushottam Kulkarni
The emergence of CXL (Compute Express Link) promises to transform the status of interconnects between host and devices and in turn impact the design of all software layers. With it…