ml-explore / ml-explore/mlx

[BUG] [CPU] Some ops fallback to fp32 implementation even fro fp64

Open
#3,047 5 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug low priority
Dominant language
C++
Stars
28.5k
Forks
2.3k
Avg merge
3d 8h
Merged PRs (30d)
62

Description

Some ops (exp, sin, cos, erf, erfinv) use the fp32 approximation for double and are hence not so accurate for double precision. Would be good to have specializations of these for double as well.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by locating the CPU implementations for exp, sin, cos, erf, and erfinv, then trace where double inputs select the fp32 approximations. Compare the available fp64 math paths and existing CPU tests, if present. Done means each listed operation uses a double-precision specialization and its accuracy is covered by validation.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
backend, performance
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
48/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.