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

[VLM] Merged multi-modal processor for InternVL-based models (#12553)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
This commit is contained in:
Cyrus Leung
2025-02-04 16:44:52 +08:00
committed by GitHub
parent 96b23621c1
commit d1ca7df84d
34 changed files with 1469 additions and 1021 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
tests/models/multimodal/processing/test_llava_onevision.py
View File

@@ -44,7 +44,10 @@ def test_processor_max_tokens(model_id):
)
processor = MULTIMODAL_REGISTRY.create_processor(
ctx.model_config,
tokenizer=cached_get_tokenizer(ctx.model_config.tokenizer),
tokenizer=cached_get_tokenizer(
ctx.model_config.tokenizer,
trust_remote_code=ctx.model_config.trust_remote_code,
),
)
info = processor.info
@@ -143,7 +146,10 @@ def test_processor_prompt_replacements_regression(model_id, num_imgs):
)
processor = MULTIMODAL_REGISTRY.create_processor(
ctx.model_config,
tokenizer=cached_get_tokenizer(ctx.model_config.tokenizer),
tokenizer=cached_get_tokenizer(
ctx.model_config.tokenizer,
trust_remote_code=ctx.model_config.trust_remote_code,
),
)
image_ratios = [(171, 152), (184, 161), (198, 176), (333, 296), (369, 328),
@@ -174,7 +180,10 @@ def test_processor_prompt_replacements_all(model_id, num_imgs):
)
processor = MULTIMODAL_REGISTRY.create_processor(
ctx.model_config,
tokenizer=cached_get_tokenizer(ctx.model_config.tokenizer),
tokenizer=cached_get_tokenizer(
ctx.model_config.tokenizer,
trust_remote_code=ctx.model_config.trust_remote_code,
),
)
seen_aspect_ratios = set[float]()