[CI] Bump huggingface-hub from v1.10.2 to v1.22.0 (#47551)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
@@ -502,7 +502,7 @@ def test_gpt2_cache_hit(monkeypatch: pytest.MonkeyPatch):
|
||||
m.setenv("VLLM_USE_AOT_COMPILE", "1")
|
||||
# First compilation - initialize model and generate
|
||||
llm_model = LLM(
|
||||
model="gpt2",
|
||||
model="openai-community/gpt2",
|
||||
compilation_config=CompilationConfig(
|
||||
mode=CompilationMode.VLLM_COMPILE,
|
||||
),
|
||||
@@ -519,7 +519,7 @@ def test_gpt2_cache_hit(monkeypatch: pytest.MonkeyPatch):
|
||||
# Second compilation - should hit cache
|
||||
m.setenv("VLLM_FORCE_AOT_LOAD", "1")
|
||||
llm_model = LLM(
|
||||
model="gpt2",
|
||||
model="openai-community/gpt2",
|
||||
compilation_config=CompilationConfig(
|
||||
mode=CompilationMode.VLLM_COMPILE,
|
||||
),
|
||||
|
||||
@@ -24,7 +24,7 @@ from vllm.utils.torch_utils import is_torch_equal_or_newer
|
||||
def get_test_models():
|
||||
"""Get list of models to test based on PyTorch version"""
|
||||
models = [
|
||||
"gpt2",
|
||||
"openai-community/gpt2",
|
||||
"Qwen/Qwen2-7B-Instruct",
|
||||
"meta-llama/Llama-3.1-8B",
|
||||
]
|
||||
|
||||
Reference in New Issue
Block a user