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

[Core][Model] Terratorch backend integration (#23513)

Browse Source 
Signed-off-by: Michele Gazzetti <michele.gazzetti1@ibm.com>
Signed-off-by: Christian Pinto <christian.pinto@ibm.com>
Co-authored-by: Christian Pinto <christian.pinto@ibm.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
This commit is contained in:
mgazz
2025-09-04 08:22:41 +01:00
committed by GitHub
parent e7fc70016f
commit 51d5e9be7d
23 changed files with 305 additions and 208 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/models/multimodal/processing/test_common.py
View File

@@ -66,7 +66,9 @@ def _test_processing_correctness(
hf_overrides=model_info.hf_overrides,
# Ensure that the cache can fit all of the data
mm_processor_cache_gb=2048,
)
skip_tokenizer_init=model_info.skip_tokenizer_init,
enforce_eager=model_info.enforce_eager,
dtype=model_info.dtype)
model_cls = MULTIMODAL_REGISTRY._get_model_cls(model_config)
factories = MULTIMODAL_REGISTRY._processor_factories[model_cls]