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

[Refactor] Pass Renderer to Input Processor (#34329)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2026-02-12 11:38:11 +08:00
committed by GitHub
parent ced2a92f40
commit b96f7314b4
20 changed files with 107 additions and 106 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
tests/models/language/pooling/test_auto_prefix_cache_support.py
View File

@@ -25,7 +25,8 @@ def test_classify_models(
with vllm_runner(
model, max_model_len=512, dtype=dtype, enable_prefix_caching=True
) as vllm_model:
cache_config = vllm_model.llm.llm_engine.cache_config
vllm_config = vllm_model.llm.llm_engine.vllm_config
cache_config = vllm_config.cache_config
assert cache_config.enable_prefix_caching
# First Run
@@ -74,7 +75,8 @@ def test_embed_models(
max_model_len=None,
enable_prefix_caching=True,
) as vllm_model:
cache_config = vllm_model.llm.llm_engine.cache_config
vllm_config = vllm_model.llm.llm_engine.vllm_config
cache_config = vllm_config.cache_config
assert cache_config.enable_prefix_caching
# First Run
@@ -106,5 +108,6 @@ def test_non_causal_models(
hf_runner, vllm_runner, example_prompts, model: str, dtype: str
) -> None:
with vllm_runner(model, max_model_len=512, dtype=dtype) as vllm_model:
cache_config = vllm_model.llm.llm_engine.cache_config
vllm_config = vllm_model.llm.llm_engine.vllm_config
cache_config = vllm_config.cache_config
assert not cache_config.enable_prefix_caching