SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

[cache] make all classes cache compatible finally (#38635)

Browse Source 
* dump

* push other models

* fix simple greedy generation

* xmod

* add fmst and clean up some mentions of old cache format

* gpt-bigcode now follows standards

* delete tuple cache reference in generation

* fix some models

* fix some models

* fix mambas and support cache in tapas

* fix some more tests

* fix copies

* delete `_reorder_cache`

* another fix copies

* fix typos and delete unnecessary test

* fix rag generate, needs special cache reordering

* fix tapas and superglue

* reformer create special cache

* recurrent gemma `reorder_cache` was a no-op, delete

* fix-copies

* fix blio and musicgen pipeline tests

* fix reformer

* fix reformer, again...

* delete `_supports_cache_class`

* delete `supports_quantized_cache`

* fix failing tests

* fix copies

* some minor clean up

* style

* style

* fix copies

* fix tests

* fix copies

* create causal mask now needs positions?

* fixc copies

* style

* Update tests/test_modeling_common.py

Co-authored-by: Joao Gante <joaofranciscocardosogante@gmail.com>

* clean-up of non-generative model after merging main

* check `is_decoder` for cache

* delete transpose for scores

* remove tuple cache from docs everywhere

* fix tests

* fix copies

* fix copies once more

* properly deprecate `encoder_attention_mask` in Bert-like models

* import `deprecate_kwarg` where needed

* fix copies again

* fix copies

* delete `nex_decoder_cache`

* fix copies asks to update for PLM

* fix copies

* rebasing had a few new models, fix them and merge asap!

* fix copies once more

* fix slow tests

* fix tests and updare PLM checkpoint

* add read token and revert accidentally removed line

* oh com -on, style

* just skip it, read token has no access to PLM yet

---------

Co-authored-by: Joao Gante <joaofranciscocardosogante@gmail.com>
This commit is contained in:
Raushan Turganbay
2025-07-16 17:00:17 +05:00
committed by GitHub
parent 6cb43defd0
commit c8524aeb07
268 changed files with 5707 additions and 6831 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
src/transformers/modeling_utils.py
View File

@@ -1971,13 +1971,9 @@ class PreTrainedModel(nn.Module, ModuleUtilsMixin, PushToHubMixin, PeftAdapterMi
# Flex Attention support
_supports_flex_attn = False
# Has support for a `Cache` instance as `past_key_values`? Does it support a `StaticCache`?
_supports_cache_class = False
# Has support `torch.compile(fullgraph=True)`
_supports_static_cache = False
# Has support for a `QuantoQuantizedCache` instance as `past_key_values`
_supports_quantized_cache = False
# A tensor parallel plan to be applied to the model when TP is enabled. For
# top-level models, this attribute is currently defined in respective model
# code. For base models, this attribute comes from