llvm / llvm/torch-mlir

is there any way to dump torchir without dense_resource via fx?

Open
#3,840 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C++
Stars
1.9k
Forks
736
Avg merge
5d 22h
Merged PRs (30d)
15

Description

How to dump torch ir without dense_resource and weight in torch-mlir?

Contributor guide

No contributing guide indexed for this repository

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

No files or tests are named. Start by tracing how torch-mlir exposes TorchIR dumping through FX, focusing on dense_resource and weight handling; clarify whether an existing option is missing or a new dumping path is requested. Done should be a confirmed, documented way to dump TorchIR without those resources, with coverage for the resulting output.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
compilers, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.