nod-ai/amd-shark-ai

(sharktank) Numerics issue with mock LM head layer test.

Open

#2,455 opened on Oct 8, 2025

View on GitHub
 (0 comments) (0 reactions) (0 assignees)Python (78 forks)github user discovery
help wanted

Repository metrics

Stars
 (67 stars)
PR merge metrics
 (PR metrics pending)

Description

       torch.testing.assert_close(actual, expected, atol=atol, rtol=rtol)
E       AssertionError: Tensor-likes are not close!
E       
E       Mismatched elements: 705 / 1024 (68.8%)
E       Greatest absolute difference: 0.00146484375 at index (1, 0, 54) (up to 0.0001 allowed)
E       Greatest relative difference: 2.34765625 at index (1, 6, 25) (up to 0 allowed)
E       
E       The failure occurred for item [0]

from https://github.com/nod-ai/shark-ai/actions/runs/18354205429/job/52281863459?pr=2289

Contributor guide

Research direction
Investigate the test for mock LM head layer to understand why tensor values differ beyond tolerance. Check if the model layer uses non deterministic operations or requires adjusted tolerances.
Tech stack
pythonpytorch
Domain
machine learningai
Issue type
Bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
PythonPyTorch
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
60