Jupyter Notebook · MIT
Exorust/TorchLeet
LeetCode for PyTorch — 65 ML/AI interview problems from real interviews at Google, Meta, Anthropic. Jupyter notebooks, an auto-grader, and an MCP AI tutor.
★ 2.6k
Stars
327 forks · 3 open issues
+3.0/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
35.1
Momentum / 100
see the breakdown below
22mo ago
Created
last push 18d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 11.5 | +3.0/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.91× the monthly pace |
| Freshness | 15 | 13.7 | last push 18d ago; decays to zero at 180 days |
| Scale | 15 | 9.9 | 2.6k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 35.1 | sum of the above |
Detail
| Topics | coding-interviewsdeep-learningfrom-scratchinterview-preparationinterview-questionsleetcodellmmachine-learning-interviewpytorchrlhftransformerstriton |
| Matched on | Learning & Roadmaps (interview-questions) |
| Short window | +21 stars over 7 days = 3.0/day |
| Long window | +86 stars over 26 days = 3.3/day |
| Lifetime average | 3.85 stars/day over 680 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |