Darius Knowledge Hub
Search
Search
Dark mode
Light mode
Explorer
Home
❯
00_Omnivore_Highlights
Folder: 00_Omnivore_Highlights
28 items under this folder.
Jan 21, 2026
A First-Principles Approach to Computer Architecture
omnivore
hardware
computer-architecture
good-read
Jan 21, 2026
A Software Engineer's Guide to Reading Research Papers
omnivore
good-read
Jan 21, 2026
A Survey of Speculative Decoding Techniques in LLM Inference
omnivore
inference
high-priority
Jan 21, 2026
CUDA Core Dump- An Effective Tool to Debug Memory Access Issues and Beyond - vLLM Blog
omnivore
gpu-programming
good-read
Jan 21, 2026
Combining NVIDIA DGX Spark + Apple Mac Studio for 4x Faster LLM Inference with EXO 1.0 - EXO
omnivore
Jan 21, 2026
Continuous batching from first principles
omnivore
inference
Jan 21, 2026
Dissecting FlashInfer - A Systems Perspective on High-Performance LLM Inference - yadnyesh's blog
omnivore
inference
ai-systems
Jan 21, 2026
ELI5- FlashAttention. Step by step explanation of how one of… - by Aleksa Gordić - Medium
omnivore
Jan 21, 2026
How Simultaneous Multithreading Works Under the Hood
omnivore
hardware
computer-architecture
high-priority
Jan 21, 2026
Inside NVIDIA GPUs- Anatomy of high performance matmul kernels - Aleksa Gordić
omnivore
gpu-programming
ai-systems
high-priority
Jan 21, 2026
LLM Inference Economics from First Principles
omnivore
inference
hardware
Jan 21, 2026
Layer-wise inferencing + batching- Small VRAM doesn't limit LLM throughput anymore
omnivore
inference
Jan 21, 2026
Max Mynter - Full Stack Machine Learning Engineer
omnivore
non-technical
Jan 21, 2026
Mechanical Sympathy- Coding for CPU Performance
omnivore
computer-architecture
good-read
Jan 21, 2026
NVIDIA DGX Spark- great hardware, early days for the ecosystem
omnivore
Jan 21, 2026
Navigating NVIDIA Nsight Systems for Efficient Profiling
omnivore
ai-systems
profiling
Jan 21, 2026
On Building Intuition in AI-ML
omnivore
Jan 21, 2026
SmolLM3- smol, multilingual, long-context reasoner
omnivore
paper
transformers
good-read
Jan 21, 2026
Smth Smth GPU Related
omnivore
gpu-programming
Jan 21, 2026
Solving Machine Learning Performance Anti-Patterns- a Systematic Approach - paulbridger.com
omnivore
ai-systems
profiling
Jan 21, 2026
Strangely, Matrix Multiplications on GPUs Run Faster When Given -Predictable- Data! [short]
omnivore
gpu-programming
good-read
Jan 21, 2026
That First CUDA Blog I Needed - Sanket Shah
omnivore
gpu-programming
good-read
high-priority
Jan 21, 2026
That First CUDA Blog I Needed -Part 2 - Sanket Shah
omnivore
gpu-programming
good-read
high-priority
Jan 21, 2026
The Bitter Lesson
omnivore
good-read
Jan 21, 2026
Vision Language Models (Better, faster, stronger)
omnivore
VLM
transformers
good-read
VLA
Jan 21, 2026
Vision Language Models Explained
omnivore
VLM
transformers
Jan 21, 2026
Yocto Linux- Build Your Own Embedded Linux Distribution - Scythe Studio
omnivore
hardware
linux
embedded
Jan 21, 2026
if you meet the singaporean on the road - eigenmoomin
omnivore
singapore