lucidrains / lucidrains/vector-quantize-pytorch

VectorQuantize not JIT-safe

Open
#8 8 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
4k
Forks
338
PR merge metrics
No merged PRs in 30d

Description

The current code controls the program based on the values of tensors (like the "initted" buffer) and will not work when compiling a jit trace.

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by locating the VectorQuantize implementation and reproducing the failure while compiling a JIT trace. Inspect how tensor values such as the "initted" buffer control execution, then verify that the same behavior works under JIT compilation without value-dependent control flow.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.