ml-ops
tech
book-notes
- Catalyst
- Algorithms to live by
- Ultralearning
- How to take smart notes
- Thinking Fast and Slow
- Creativity Inc
- Range
- Design of Everyday Things
introduction
diy-productivity
- Lossless learning
- Good Resumes
- LNO framework for productivity
- How I journal
- DIY Productivity
- How I take notes
- Inbox zero and mail categorization
thoughtful-ramblings
research-papers
- Things read 2025 JFM
- CLIP
- Attention sinks
- Quantization
- LLM Inference Part 1
- Things read in 2024 JFM
- Things read in 2023 OND
- Whisper
- AST Audio Spectrogram Transformer
- Swin transformers
deep-learning
- CLIP
- Short intro to VQ VAEs
- Whisper
- Quickstart on LLMs
- Word Embeddings
- Batchnorm
- AST Audio Spectrogram Transformer
- Swin transformers
machine-learning
learnings
llms
- Quantization
- LLM Inference Part 1
- Things read in 2024 JFM
- Agents
- Things read in 2023 OND
- Quickstart on LLMs
computer-vision
multimodal
agents
gpus
- Cutlass primer
- Mechanics of FP8 for LLMs
- What is Systems for LLM
- GPU chip design tradeoffs
- LLM Inference Part 1
llm-optimization
- torch.compile integration with vLLM
- Cutlass primer
- The curious case of weight tying in LoRA
- Mechanics of FP8 for LLMs
- Attention sinks
- LLM Inference Part 1