biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[feat] Enable mm caching for transformers backend (#21358)

Browse Source 
Signed-off-by: raushan <raushan@huggingface.co>
This commit is contained in:
Raushan Turganbay
2025-07-22 17:18:46 +02:00
committed by GitHub
parent b194557a6c
commit f38ee34a0a
4 changed files with 7 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
tests/models/multimodal/generation/test_common.py
View File

@@ -186,8 +186,6 @@ VLM_TEST_SETTINGS = {
image_size_factors=[(0.25, 0.5, 1.0)],
vllm_runner_kwargs={
"model_impl": "transformers",
"disable_mm_preprocessor_cache": True,
"enable_prefix_caching": False,
},
marks=[pytest.mark.core_model],
),
@@ -205,8 +203,6 @@ VLM_TEST_SETTINGS = {
# image_size_factors=[(0.25, 0.5, 1.0)],
# vllm_runner_kwargs={
# "model_impl": "transformers",
# "disable_mm_preprocessor_cache": True,
# "enable_prefix_caching": False,
# },
# marks=[pytest.mark.core_model],
# ),
@@ -223,8 +219,6 @@ VLM_TEST_SETTINGS = {
image_size_factors=[(0.25, 0.2, 0.15)],
vllm_runner_kwargs={
"model_impl": "transformers",
"disable_mm_preprocessor_cache": True,
"enable_prefix_caching": False,
},
marks=[large_gpu_mark(min_gb=32)],
),
@@ -239,8 +233,6 @@ VLM_TEST_SETTINGS = {
image_size_factors=[(0.25, 0.5, 1.0)],
vllm_runner_kwargs={
"model_impl": "auto",
"disable_mm_preprocessor_cache": True,
"enable_prefix_caching": False,
},
auto_cls=AutoModelForImageTextToText,
marks=[pytest.mark.core_model],