Zenaique
Topics
Practice
Browse
Reference
Challenges
Pricing
Search…
⌘K
Topics
/
Inference Optimization
/
All Reduce
All Reduce
Subtopic
1 questions
Questions tagged with All Reduce — part of Inference Optimization.
Format
Difficulty
Role
Experience
Companies
Sort
Newest
Quality
Difficulty ↑
Difficulty ↓
Questions
Walk through how tensor parallelism shards one matmul across GPUs and what it adds to decode step time
Short Answer
Medium
·
Qual 4.0
NVIDIA