Welcome to my small corner of the internet where I share things I’m learning, building, and exploring.
- I work as MLOps Engineer at Fuzzy Labs
- You can find me on the following socials.
Where vLLM Cold-Start Time Goes on GKE?
Measuring vLLM cold-start bottlenecks on GKE and evaluating ways to reduce time to first request.
Docker and Pals
Architecture components of Docker
Pipeline Parallelism Revisited - Implementations using PyTorch
Implementing and profiling pipeline parallelism techniques using PyTorch
TIL - Cloud VMs, microVM, Unikernels and hypervisors
Anatomy of different layers of abstractions for a cloud compute
ZeRO Sharding Revisited - Implementations using PyTorch
Implement ZeRO sharding strategies using PyTorch