Independent project. Not a U.S. government website.

Support our project (opens Buy Me a Coffee)
USASI

Pankaj Gupta

Co-founder of Baseten who writes on model performance optimization for LLM, image and video inference

Pankaj Gupta is a co-founder of Baseten, which runs inference for open and custom AI models. Gupta's posts on the Baseten blog cover the company's model performance work, including its adoption of TensorRT-LLM, speculative decoding and inference benchmarks on NVIDIA GH200, and later work on kernel-level optimization for image generation models.1234

Model performance at Baseten

Gupta is listed on Baseten's blog as a co-founder. In January 2025, Gupta wrote a review of the company's 2024 model performance work, which described adopting TensorRT-LLM as the core framework, using NVIDIA's Hopper architecture and supporting production-ready speculative decoding.12

With Philip Kiely, Gupta tested Llama 3.3 70B inference on a single NVIDIA GH200 in Lambda Cloud (February 2025). In August 2026, Gupta co-authored a post with Brian Li and Faraz Shahsavan on Baseten's agentic kernel optimization framework for image models such as Qwen-Image and FLUX.2.34

Work

Career timeline

  1. Jan 9, 2025

    Published Baseten's review of its 2024 model performance optimization work.2

  2. Feb 7, 2025

    Co-authored a test of Llama 3.3 70B inference on NVIDIA GH200 in Lambda Cloud.3

  3. Aug 29, 2026

    Co-authored a post on Baseten's agentic kernel optimization framework.4

More sourced profiles at the same organization, in the same field, or from the same school.

Is this you?

Profiles cover public professional work only, and every line cites a source. If something is out of date, missing or wrong, send a correction with a link to an official page and we will update it. Suggest a correction

Profile on USASIAdd this badge to your website or GitHub profile README. It links back to this page. It is not an endorsement or a rating.

Markdown (for a README)

[![Pankaj Gupta — Profile on USASI](https://unitedstatesofamericasuperintelligence.com/badges/profile.svg)](https://unitedstatesofamericasuperintelligence.com/people/pankaj-gupta/)

HTML

<a href="https://unitedstatesofamericasuperintelligence.com/people/pankaj-gupta/"><img src="https://unitedstatesofamericasuperintelligence.com/badges/profile.svg" alt="Pankaj Gupta — Profile on USASI" height="20"></a>

This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.

References · reviewed Oct 22, 2026

  1. 1.
  2. 2.
    Driving model performance optimization: 2024 highlights (external site: baseten.co)

    Baseten · Announcement · published Jan 9, 2025 · accessed Oct 22, 2026

  3. 3.
    Testing Llama 3.3 70B inference performance on NVIDIA GH200 in Lambda Cloud (external site: baseten.co)

    Baseten · Announcement · published Feb 7, 2025 · accessed Oct 22, 2026

  4. 4.
    Agentic kernels in production (external site: baseten.co)

    Baseten · Announcement · published Aug 29, 2026 · accessed Oct 22, 2026

Support Us

Help keep USASI useful.

Optional. No USASI account required. Payment takes place on the linked provider’s website (Buy Me a Coffee).

About supporting this project