Back

transformers #43757

Avoid hard failure for gpt-oss GGUF architecture by falling back to g…

by TheSanjBot · Feb 06, 2026 at 19:26 UTC · scan-997359b9f8b12067

View on Github · Download JSON
Medium Risk (25%)

Get this automatically on every PR

Install the Axiomo GitHub App to get Signals as check runs and PR comments on every pull request.

Install App

Risk Assessment

Risk level: Medium (25%)

Risk Drivers

  • new_contributor: First contribution from TheSanjBot

Intent

4/4 criteria met

Avoid hard failure for gpt-oss GGUF architecture by falling back to gpt-neox.

Non-Goals

  • - Implement full GPT-OSS support
  • - Support MoE layers
  • - Guarantee inference correctness

Acceptance Criteria

  • ✓
    GGUF models with `gpt-oss` architecture should not trigger a hard failure.

    modeling_gguf_pytorch_utils.py line 462+ maps `gpt-oss` to `gpt-neox`

  • ✓
    Warning message is emitted for `gpt-oss` use.

    modeling_gguf_pytorch_utils.py line 465 emits warning

  • ✓
    No changes to support MoE layers.

    No MoE-related changes in diff

  • ✓
    No guarantee of inference correctness.

    Warning message states no correctness guarantee

Confidence: 95.0% Source: pr description AI: openai

Contributors

TheSanjBot PR Author 4 commits ? New Contributor
Account Age: 2013 days
Prior PRs: 1

First-time contributor to this repository. unfamiliar with 2 files.

Evidence

Evidence Completeness: 10.0%
tests_passing Failing
Missing: ci_passing, lint_passing, security_scan_clean, coverage_maintained, build_successful

Supply Chain

None Risk
Modifies dependencies
Modifies lockfile
Modifies CI config
Modifies build scripts

Focus Files

Review 2 file(s)

src/transformers/models/grounding_dino/processing_grounding_dino.py +8

Source code

medium
src/transformers/modeling_gguf_pytorch_utils.py +7

Source code

medium

Triage

10

minutes to review

low

effort level

none

staleness risk

Standard review process

Recommendation

NEEDS DISCUSSION 36.0% readiness

Insufficient evidence (CI/tests) to evaluate

Next Steps

Question

Why is ci_passing missing? Consider adding this check.

Question

Why is lint_passing missing? Consider adding this check.

Nitpick

First contribution - consider welcoming and providing extra context