Nitin Gupta

Summary Problem: Multi-model workloads are the norm: A/B tests, customer fine-tunes, safety variants, multi-stage pipelines.

I keep running into the same pattern when trying to self-host models (which is a lot of fun): we run several big models side by side, all of them valuable, all of them slightly different, and all of them wasting VRAM by reloading nearly the same weights.

This feature has now been accepted and merged in the upstream kernel and will be part of kernel release 5.9.

Some drivers needs to allocate almost all memory as hugepages to reduce (on-device or CPU) TLB pressure.

We built an object store from scratch in Elixir using a layered design approach.

Part I, introduces the overall design of our object store.

Part I, introduces the overall design of our object store.

Part I layer.

Part I, introduces the overall design of our object store.

I recently designed an object store from scratch in Elixir.

Elixir is a function programming language that I have been using a lot in recent months to build all kinds of applications.

I recently stumbled upon a subtle bug in a benchmark code which again reminds me to never use C++ again, if I can.

For some time I’ve been looking for a backup solution for Linux that can periodically take snapshots of data, allowing me to go back in history of any file just like git.

There is no official Google drive client for Linux.

Often, you have more than one system at your disposal but no clear way of distributing your compilation workloads over to all or some of them.

Recently, I developed Linux kernel driver which creates generic RAM based compressed block devices (called zram).

Since a long time, I was looking for a graphical git diff viewer which could show original and modified file side-by-side and highlight the changes.

You worked on some part of Linux kernel.

In case you are unfamiliar with ccache, its a “compiler cache”.

Linux kernel has few SLAB allocator variants included: SLAB, SLUB and SLOB.

Very old but still as relevant… and very interesting too!

One of my Fedora 10 systems used to freeze very frequently.

Here is link to paper (pdf) (MP3) Recently I came across this paper published in OSDI ‘08.