NVIDIA / NVIDIA/Model-Optimizer

Puzzletron OOM during step 6 (one-block scoring) for Qwen 3.5-2B VLM

Open
#1,779 1 comment 0 reactions 1 assignee View on GitHub

@danielkorzekwa is already working on this.

Since Jun 21, 2026.

bug
Dominant language
Python
Stars
3.8k
Forks
604
Avg merge
2d 8h
Merged PRs (30d)
142

Description

branch: dkorzekwa/claude_qwen35

Environment: 2× H100 80GB, Puzzletron full pipeline, nproc_per_node=2

Model: Qwen3.5-2B (model_type: qwen3_5, a VLM with nested text_config)

Failure: torch.OutOfMemoryError on GPU 1 during step 6 ("calculating one block scores"), with ~74 GiB consumed out of 80 GiB.

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.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.