vashistht Goto Github PK

I am now at CMU doing a masters in AI Engineering. I did my undergrad in physics and math at the Univesrity of Rochester. Most of the work here is from my classes and previous work on the Dark Energy Spectropic Instrument (DESI) (about the development of machine learning tools to identify and classify transients in galaxy spectra).

• Current: Speculative Decoding for Faster LLM Inference: I am currently working on speculative decoding and the work is advised by Professor Beidi Chen.

• Los Alamos National Lab A preview of what I worked on during my time @LosAlamosNationalLab is on the repo here

• Project Background (DESI): During the DESI survey we expect to find galaxies that host bright transients such as supernovae, compact binary mergers, etc. The identification of transients is important not only to ensure correct estimates of the host redshifts but also because it provides an opportunity to obtain “serendipitous” spectra of the transients themselves.
  

• 📫 How to reach me: Linkedin, Email: [email protected]