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

Cache: init empty cache when use_cache (#34274)

Browse Source 
* fix

* fix tests

* fix copies

* add docs

* Revert "add docs"

This reverts commit 32d35634f12ba02781d2ebdee0c8dcfbe992a7b9.

* qwen move deltas

* mllama can potentiall fullgraph compile

* enable mllama compile and fix tests

* remove mllama fixes
This commit is contained in:
Raushan Turganbay
2024-11-25 10:11:33 +01:00
committed by GitHub
parent 1339a14dca
commit c1a8520419
7 changed files with 57 additions and 64 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/models/qwen2_vl/test_modeling_qwen2_vl.py
View File

@@ -333,6 +333,10 @@ class Qwen2VLModelTest(ModelTesterMixin, GenerationTesterMixin, unittest.TestCas
def test_generate_from_inputs_embeds_with_static_cache(self):
pass
@unittest.skip(reason="Can't compile fullgraph due to dynamic control flow in `prepare_inputs_for_generate`")
def test_generate_compile_fullgraph(self):
pass
@require_torch
class Qwen2VLIntegrationTest(unittest.TestCase):