Blog table of contents
Search posts
Search
Inference and serving
1
The KV Cache Is an Allocator Problem
[Jul 19, 2026]
♥
0
Distributed training
3
A Restart Is Not a Resume: Testing PyTorch Checkpoints
[Jul 04, 2026]
♥
0
Tensor Parallelism
2
Tensor Parallelism II: GQA Attention, One Head Group at a Time
[Jul 16, 2026]
♥
0
Tensor Parallelism I: Rebuilding a Megatron SwiGLU Block Across Two Ranks
[Jul 16, 2026]
♥
0
Multimodal learning
1
Pixels Are Not Positions: Testing 2D Coordinate Encodings Under Scale and Translation
[Jul 10, 2026]
♥
0
Book Recommendations 2026
8
Circe
by Madeline Miller
Pachinko
by Min Jin Lee
The Staff Engineer's Path
by Tanya Reilly
Man's Search for Meaning
by Viktor E. Frankl
The Thinking Machine
by Stephen Witt
The Emperor of All Maladies
by Siddhartha Mukherjee
Visit India with Me
by Dhan Gopal Mukerji
A Mind at Play
by Jimmy Soni and Rob Goodman
No matching posts.