Anjali Shah

Anjali Shah is a senior deep learning scientist at NVIDIA within the Developer Advocate Engineering group helping clients build generative AI solutions. Early in her career, as a software engineer, she built mission-critical platforms for the world's leading financial services firms. She then spent several years in the healthcare sector, architecting and implementing large scale healthcare (EHR) systems. Before joining NVIDIA, she spent several years at a leading tech company, working across different industries helping clients build innovative data and AI solutions. She has a Ph.D. in biomedical informatics and applied statistics and an M.S. and B.S. in computer science and engineering.
Avatar photo

Posts by Anjali Shah

Generative AI Jan 16, 2025

Introducing New KV Cache Reuse Optimizations in NVIDIA TensorRT-LLM

Language models generate text by predicting the next token, given all the previous tokens including the input text tokens. Key and value elements of the... 7 MIN READ
Generative AI Dec 17, 2024

Boost Llama 3.3 70B Inference Throughput 3x with NVIDIA TensorRT-LLM Speculative Decoding

Meta's Llama collection of open large language models (LLMs) continues to grow with the recent addition of Llama 3.3 70B, a text-only... 8 MIN READ
Chat avatar between tiles with computer activity icons, on a black background.
Generative AI Dec 11, 2024

NVIDIA TensorRT-LLM Now Accelerates Encoder-Decoder Models with In-Flight Batching

NVIDIA recently announced that NVIDIA TensorRT-LLM now accelerates encoder-decoder model architectures. TensorRT-LLM is an open-source library that optimizes... 4 MIN READ
Image of the TensorRT-LLM icon next to multiple other icons of computer activities.
Generative AI Dec 02, 2024

TensorRT-LLM Speculative Decoding Boosts Inference Throughput by up to 3.6x

NVIDIA TensorRT-LLM support for speculative decoding now provides over 3x the speedup in total token throughput. TensorRT-LLM is an open-source library that... 9 MIN READ
Top Stories Nov 19, 2024

Llama 3.2 Full-Stack Optimizations Unlock High Performance on NVIDIA GPUs

Meta recently released its Llama 3.2 series of vision language models (VLMs), which come in 11B parameter and 90B parameter variants. These models are... 6 MIN READ
Generative AI Sep 25, 2024

Deploying Accelerated Llama 3.2 from the Edge to the Cloud

Expanding the open-source Meta Llama collection of models, the Llama 3.2 collection includes vision language models (VLMs), small language models (SLMs), and an... 6 MIN READ