π Software engineer at NVIDIA, working on LLM inference on the Dynamo team.
π Off the clock: sci-fi novels π, basketball π, tennis πΎ, volleyball π.
π LinkedIn
Forked from mitsuhiko/minijinja
MiniJinja is a powerful but minimal dependency template engine for Rust compatible with Jinja/Jinja2
Rust
Forked from sgl-project/sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
Python
Forked from vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Python