no_rope_layer_interval is declared but never applied, and SmolLM3's own config sets it

Ouverte
  • Quelque chose ne va pas ?
#22,043 2 commentaires 0 réactions 2 personnes assignées Voir sur GitHub

Les mainteneurs répondent en général sous 1 jour

@MukeshK17 y travaille déjà.

Depuis le 24/8/2026.

  • #22177 par @MukeshK17 — ouverte

Évaluation

Cette issue n'a pas encore été évaluée.

Description

module: llm triaged

ModelArgs declares no_rope_layer_interval, and examples/models/smollm3/3b_config.json sets it to 4, but nothing on the examples/models/llama export path reads it. On main (e4576d0) the name appears exactly once across the 32 Python files of that path:

examples/models/llama/model_args.py:119:    no_rope_layer_interval: Optional[int] = (

__post_init__ does not touch it, and Attention.forward applies rope unconditionally (attention.py:529, attention.py:563) with no layer-index test. The two places that do honour it are backends/mlx/llm/et_attention.py:111 and examples/qualcomm/oss_scripts/llama/model/static_llama.py:288.

So a model that alternates RoPE and NoPE layers exports without complaint and comes out with rope on every layer.

Reproducing

examples/models/smollm3/3b_config.json and examples/models/smollm3/convert_weights.py are both in the tree, so SmolLM3-3B looks ready to export. Converting its weights and exporting through export_llm with that params json (XNNPACK, 8da4w + 8-bit embedding, 1852.2 MB) gives a .pte that loads and runs, then does this:

prompt: <|im_start|>user\nWhat is the capital of France?<|im_end|>\n<|im_start|>assistant\n
output: Okay, so you want to know what what what what what what what what what what what
        what what what what what what what what what what what what what what what what

prompt: <|im_start|>user\nWhat is 17 times 4?<|im_end|>\n<|im_start|>assistant\n
output: I think you are looking for an answer that can be given that can be be be be be
        determ determ determ determ determ determ determ determ determ determ#ae determ#

It starts as English and collapses, which is what a positional-encoding mismatch looks like: the first few tokens are fine and the drift grows with position.

What would help

Either implement the interval on this path, or reject a params json that sets a field the chosen backend does not implement. The silent version is the expensive one — the export succeeds, the file is the right size, and the model is simply a different model.

Measured with the executorch 1.4.0 wheel; the code paths quoted above are byte-identical on main at e4576d0.

cc @larryliu0820 @mergennachin @cccclai @helunwencser @jackzhxng @digantdesai

Langage dominant
Python
Étoiles
5.1k
Forks
1.2k
Merge moyen
1 j 18 h
PR mergées (30 j)
668

Préparer son environnement

Par où commencer

  1. Lisez l'issue en entier, puis le guide de contribution du projet.
  2. Signalez en commentaire que vous la prenez — cela évite que deux personnes fassent le même travail.
  3. Forkez le dépôt et travaillez sur une branche.
  4. Ouvrez une pull request qui référence le numéro de l'issue.

Autres issues de pytorch/executorch

Toutes les issues de pytorch/executorch

Issues similaires

Plus d'issues Python

Recevez les nouvelles issues par e-mail

Un résumé court des issues GitHub adaptées aux débutants.