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

[Core] Update dtype detection and defaults (#14858)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2025-03-19 13:49:33 +08:00
committed by GitHub
parent 8b3e94a357
commit f690372b68
22 changed files with 175 additions and 227 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/tensorizer_loader/test_tensorizer.py
View File

@@ -166,7 +166,7 @@ def test_vllm_model_can_load_with_lora(vllm_runner, tmp_path):
test_prompts = multilora_inference.create_test_prompts(lora_path)
# Serialize model before deserializing and binding LoRA adapters
with vllm_runner(model_ref, ) as vllm_model:
with vllm_runner(model_ref) as vllm_model:
model_path = tmp_path / (model_ref + ".tensors")
vllm_model.apply_model(
@@ -208,7 +208,7 @@ def test_load_without_tensorizer_load_format(vllm_runner):
@pytest.mark.skipif(not is_curl_installed(), reason="cURL is not installed")
def test_openai_apiserver_with_tensorizer(vllm_runner, tmp_path):
## Serialize model
with vllm_runner(model_ref, ) as vllm_model:
with vllm_runner(model_ref) as vllm_model:
model_path = tmp_path / (model_ref + ".tensors")
vllm_model.apply_model(