CI(Core): expand KNOWN_BROKEN_COMPILE with 7 latest-transformers failures

The previous matrix run on commit 7855571a tripped on 7 model_types
not in my initial list (which I built from transformers 4.57.6).
Latest 5.x ships more model_types; same regex/source-rewriter
failure modes:

  audioflamingo3   emitted file: unterminated string literal
  colmodernvbert   string index out of range
  gemma4_assistant string index out of range
  musicflamingo    emitted file: unterminated string literal
  sam3_lite_text   name 'Sam3LiteTextLayerScaledResidual' is not defined
  voxtral          emitted file: unterminated string literal
  voxtral_realtime emitted file: unterminated string literal

Added each to KNOWN_BROKEN_COMPILE under the appropriate failure
category (string-index, unterminated-string, undefined-name). Same
contract as before -- new failures NOT in this list still fail the
cell. The unterminated-string family (4 of 7) is a NEW failure
category; documented as Category B-2.
This commit is contained in:
Daniel Han 2026-05-07 09:17:47 +00:00
commit 694d88ccab

View file

@ -858,31 +858,39 @@ jobs:
# for a follow-up unsloth-zoo PR.
KNOWN_BROKEN_COMPILE = {
# Category A: `string index out of range` in source rewriter.
"colpali": "string index out of range",
"colqwen2": "string index out of range",
"dpr": "string index out of range",
"rag": "string index out of range",
"shieldgemma2": "string index out of range",
"timm_backbone": "string index out of range",
"colpali": "string index out of range",
"colqwen2": "string index out of range",
"colmodernvbert": "string index out of range",
"dpr": "string index out of range",
"gemma4_assistant":"string index out of range",
"rag": "string index out of range",
"shieldgemma2": "string index out of range",
"timm_backbone": "string index out of range",
# Category B: rewriter emits invalid Python source.
"clvp": "emitted file: unexpected indent",
"electra": "emitted file: expected ':'",
"falcon_mamba": "emitted file: unexpected indent",
"gpt2": "emitted file: unexpected indent",
"imagegpt": "emitted file: unexpected indent",
"mamba": "emitted file: unexpected indent",
"tapas": "emitted file: expected ':'",
"xlstm": "emitted file: unexpected indent",
"clvp": "emitted file: unexpected indent",
"electra": "emitted file: expected ':'",
"falcon_mamba": "emitted file: unexpected indent",
"gpt2": "emitted file: unexpected indent",
"imagegpt": "emitted file: unexpected indent",
"mamba": "emitted file: unexpected indent",
"tapas": "emitted file: expected ':'",
"xlstm": "emitted file: unexpected indent",
# Category B-2: emit unterminated string literal (latest tf).
"audioflamingo3": "emitted file: unterminated string literal",
"musicflamingo": "emitted file: unterminated string literal",
"voxtral": "emitted file: unterminated string literal",
"voxtral_realtime":"emitted file: unterminated string literal",
# Category C: rewriter emits unclosed paren.
"kosmos2": "emitted file: '(' was never closed",
"kosmos2_5": "emitted file: '(' was never closed",
"kosmos2": "emitted file: '(' was never closed",
"kosmos2_5": "emitted file: '(' was never closed",
# Category D: imports list builder picks up a non-exported name.
"auto": "module has no attribute _BaseModelWithGenerate",
"bit": "module has no attribute Linear",
"regnet": "module has no attribute Linear",
"resnet": "module has no attribute Linear",
"auto": "module has no attribute _BaseModelWithGenerate",
"bit": "module has no attribute Linear",
"regnet": "module has no attribute Linear",
"resnet": "module has no attribute Linear",
# Category E: undefined name in emitted file.
"perceiver": "name 'AbstractPreprocessor' is not defined",
"perceiver": "name 'AbstractPreprocessor' is not defined",
"sam3_lite_text": "name 'Sam3LiteTextLayerScaledResidual' is not defined",
}