- mlsys
- transformer
- paper-summaries
- MLSys
- LLMs
- PPML
•
•
•
•
•
-
Paper Summary #14 - Physics of Language Models: Part 3.1, Knowledge Storage and Extraction
My notes from the Physics of Language Models series of papers.
-
Understanding Multi-Head Latent Attention (MLA)
A mathematical and code deep-dive on one of the key innovations from Deepseek - Multihead Latent Attention (MLA)
-
Deriving the Gradient for the Backward Pass of Layer Normalization
Understanding the math behind Layer Normalization and deriving the gradients for the backward pass.
-
Notes from GTC'25: CUDA Techniques to Maximize Compute and Instruction Throughput
My notes from the talk on maximizing compute and instruction throughput at NVIDIA GTC 2025.
-
Notes from GTC'25: CUDA Techniques to Maximize Memory Bandwidth and Hide Latency - Part 2
Second part of my notes from the talk on maximizing memory bandwidth at NVIDIA GTC 2025.
-
Notes from GTC'25: CUDA Techniques to Maximize Memory Bandwidth and Hide Latency - Part 1
First part of my notes from the talk on maximizing memory bandwidth at NVIDIA GTC 2025.
-
Faster Cross-Encoder Inference: Unleashing torch.compile for speed
A quick writeup on accelerating a Jina Cross-Encoder using torch.compile
-
Paper Summary #13 - Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process
My notes from the Physics of Language Models series of papers.
-
Paper Summary #12 - Image Recaptioning in DALL-E 3
The image recaptioning technique used in DALL-E 3 was extended to videos in Sora.
-
Paper Summary #11 - Sora
OpenAI announced a ground-breaking text-to-video diffusion model capable of generating high-definition videos up to 60 seconds long.
