majiayu000 abd1dbc548 [Bugfix] Preserve original tokenizer class name in CachedTokenizer ...

HuggingFace transformers processor validates tokenizer type by checking
the class name. When vLLM creates a CachedTokenizer with a modified
class name (e.g., 'CachedQwen2TokenizerFast'), the processor type check
fails with TypeError.

This fix preserves the original tokenizer class name and qualname in
CachedTokenizer, ensuring compatibility with HuggingFace transformers
processor type checking.

Fixes #31080

Signed-off-by: Claude <noreply@anthropic.com>
Signed-off-by: majiayu000 <1835304752@qq.com>

2025-12-24 16:02:48 +08:00

..

__init__.py

…

test_basic.py

[Refactor] TokenizerRegistry only uses lazy imports (#30609)

2025-12-13 23:16:22 +08:00

test_detokenize.py

[CI Failure] Disable mosaicml/mpt-7b and databricks/dbrx-instruct tests (#31182)

2025-12-22 15:40:35 -08:00

test_hf.py

[Bugfix] Preserve original tokenizer class name in CachedTokenizer

2025-12-24 16:02:48 +08:00

test_mistral.py

Add Mistral Large 3 and Ministral 3 (#29757)

2025-12-02 10:29:00 +00:00

test_registry.py

[Refactor] TokenizerRegistry only uses lazy imports (#30609)

2025-12-13 23:16:22 +08:00