[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:
Harry Mellor
2026-07-04 07:45:45 -07:00
committed by GitHub
parent 1d354c694e
commit f1445f6dbd
25 changed files with 49 additions and 45 deletions
+1 -1
View File
@@ -21,7 +21,7 @@ def _patch_hf_api(side_effect):
@pytest.fixture(scope="session")
def hf_tokenizer() -> PreTrainedTokenizerBase:
return AutoTokenizer.from_pretrained("gpt2")
return AutoTokenizer.from_pretrained("openai-community/gpt2")
_FAKE_ROWS = {
+1 -1
View File
@@ -12,7 +12,7 @@ from vllm.benchmarks.datasets import get_samples
@pytest.fixture(scope="session")
def hf_tokenizer() -> PreTrainedTokenizerBase:
return AutoTokenizer.from_pretrained("gpt2")
return AutoTokenizer.from_pretrained("openai-community/gpt2")
def _write_jsonl(path: Path, n_rows: int) -> None:
+1 -1
View File
@@ -17,7 +17,7 @@ from vllm.benchmarks.datasets import (
@pytest.fixture(scope="session")
def hf_tokenizer() -> PreTrainedTokenizerBase:
# Use a small, commonly available tokenizer
return AutoTokenizer.from_pretrained("gpt2")
return AutoTokenizer.from_pretrained("openai-community/gpt2")
class Params(NamedTuple):
@@ -16,7 +16,7 @@ from vllm.benchmarks.datasets import RandomMultiModalDataset, SampleRequest
@pytest.fixture(scope="session")
def hf_tokenizer() -> PreTrainedTokenizerBase:
"""Use a small, commonly available tokenizer."""
return AutoTokenizer.from_pretrained("gpt2")
return AutoTokenizer.from_pretrained("openai-community/gpt2")
@pytest.fixture
+2 -2
View File
@@ -13,7 +13,7 @@ from vllm.benchmarks.datasets.create_txt_slices_dataset import create_txt_slices
@pytest.fixture(scope="session")
def hf_tokenizer() -> PreTrainedTokenizerBase:
# Use a small, commonly available tokenizer
return AutoTokenizer.from_pretrained("gpt2")
return AutoTokenizer.from_pretrained("openai-community/gpt2")
text_content = """
@@ -39,7 +39,7 @@ def test_create_txt_slices_jsonl(
create_txt_slices_jsonl(
input_path=str(txt_path),
output_path=str(jsonl_path),
tokenizer_name="gpt2",
tokenizer_name="openai-community/gpt2",
num_prompts=10,
input_len=10,
output_len=10,