Poster · Sydney
In STeP: Speculative Tensor Parallelism for Concurrent Heterogeneous Inference of LLMs
- When
- Wed 9 Dec 2026, 17:00–20:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 4
- Authors
- Viren Luke Radhakrishnan, Dhruva Kashyap, Pranav K Nayak, Chiranjib Bhattacharyya, Prakash Raghavendra
- Organisations
- AMD, Indian Institute of Science, HP AI Lab
- QRS classification
- Language models