abhishek sharma

Waiting for Godot

[abhishek sharma @asreddevils]

Built an open-source RLM (Recursive Language Models) package in Python!

Solves LLM "context rot" by treating context as a programmable object the model explores recursively.

Credits:
- @rasmus1610 for the initial implementation inspiration

[Marius Vach @rasmus1610]

Here is the solveit dialog implementing RLMs by @a1zhang using `lisette` and `toolslm` by @answerdotai (h/t @jeremyphoward)

[abhishek sharma @asreddevils]

Thankyou @AirIndiaX for the lovely check-in experience and hospitality. 10/10 would recommend. Special thanks to Simran Raina, Jagdish Raj, Abhinay Kumar and Dev Singh 😍🎊🔥

[abhishek sharma @asreddevils]

Unsloth Puzzles: https://t.co/JK6KFzzyok

[abhishek sharma @asreddevils]

🧵 I wrote my first GPU kernel solving @UnslothAI 's challenge A

Here's everything I learned about NF4 quantization and Triton

Starting from absolute zero → working kernel in 3 days

Let's go 👇

[abhishek sharma @asreddevils]

Full post includes:

✅ Toy examples (dequantize one number by hand)
✅ Every broken version of the kernel
✅ Line-by-line explanation of the final code
✅ What custom PTX assembly could add

For anyone learning GPU programming: https://t.co/WEBhJuRkpK

[abhishek sharma @asreddevils]

Thanks to @UnslothAI for Challenge B that started this rabbit hole.

What began as a competition became a masterclass in distributed systems + quantization internals.

Sometimes the best learning comes from "impossible" problems. 🦙

[abhishek sharma @asreddevils]

🧵 How to train Llama 3.1 8B on 2 consumer GPUs using FSDP2 + QLoRA.

Here's how it works (and what broke along the way):

[abhishek sharma @asreddevils]

The lesson: tools built by different teams don't always compose cleanly.

The skill: reading source code, understanding assumptions, finding escape hatches.

Full blog with complete code: https://t.co/v5K7Ha209f

[abhishek sharma @asreddevils]

If you're into ML systems or LLM training, let's connect! 🚀

#MachineLearning #PyTorch #LLM

[abhishek sharma @asreddevils]

@UnslothAI Challenge E on memory-efficient backpropagation 🧵

Problem: LLMs with 128K vocab = 4-8GB VRAM just for logits

Solution: Custom autograd + gradient checkpointing

Results: 46% memory savings, verified on real models

Here's what I learned 👇

[abhishek sharma @asreddevils]

Full writeup with code, mistakes, and insights: https://t.co/zelJSP47xh