Make bare hugging_face imports forbidden (#49726)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
This commit is contained in:
Harry Mellor
2026-07-25 04:18:39 -07:00
committed by GitHub
co-authored by Andreas Karatzas
parent 0b1a8bb1f6
commit ca0defa343
29 changed files with 199 additions and 106 deletions
@@ -12,10 +12,10 @@ import pytest_asyncio
import safetensors
import torch
import torch.nn as nn
from huggingface_hub import hf_hub_download
from transformers import AutoConfig, AutoTokenizer
from tests.utils import RemoteOpenAIServer
from vllm.transformers_utils.repo_utils import hf_api
from vllm.utils.serial_utils import tensor2base64
from vllm.utils.torch_utils import is_torch_equal_or_newer
@@ -126,11 +126,13 @@ def qwen2audio_aligned_content_and_embeds_b64() -> tuple[str, str]:
content = "Describe this audio."
tokenizer = AutoTokenizer.from_pretrained(QWEN2AUDIO_MODEL, trust_remote_code=True)
index_path = hf_hub_download(QWEN2AUDIO_MODEL, "model.safetensors.index.json")
index_path = hf_api().hf_hub_download(
QWEN2AUDIO_MODEL, "model.safetensors.index.json"
)
with open(index_path) as f:
weight_map = json.load(f)["weight_map"]
embed_key = next(k for k in weight_map if k.endswith("embed_tokens.weight"))
shard_path = hf_hub_download(QWEN2AUDIO_MODEL, weight_map[embed_key])
shard_path = hf_api().hf_hub_download(QWEN2AUDIO_MODEL, weight_map[embed_key])
with safetensors.safe_open(shard_path, framework="pt", device="cpu") as f:
embed_weight = f.get_tensor(embed_key)
embed_layer = nn.Embedding.from_pretrained(embed_weight.to(QWEN2AUDIO_DTYPE))
@@ -13,12 +13,12 @@ import pytest_asyncio
import safetensors
import torch
import torch.nn as nn
from huggingface_hub import hf_hub_download
from transformers import AutoTokenizer
from tests.utils import RemoteOpenAIServer
from vllm.assets.image import ImageAsset
from vllm.multimodal.utils import encode_image_url
from vllm.transformers_utils.repo_utils import hf_api
from vllm.utils.serial_utils import tensor2base64
MODEL_NAME = "Qwen/Qwen2-VL-2B-Instruct"
@@ -84,11 +84,11 @@ def aligned_content_and_embeds_b64() -> tuple[str, str]:
content = "Describe this image."
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, trust_remote_code=True)
index_path = hf_hub_download(MODEL_NAME, "model.safetensors.index.json")
index_path = hf_api().hf_hub_download(MODEL_NAME, "model.safetensors.index.json")
with open(index_path) as f:
weight_map = json.load(f)["weight_map"]
embed_key = next(k for k in weight_map if k.endswith("embed_tokens.weight"))
shard_path = hf_hub_download(MODEL_NAME, weight_map[embed_key])
shard_path = hf_api().hf_hub_download(MODEL_NAME, weight_map[embed_key])
with safetensors.safe_open(shard_path, framework="pt", device="cpu") as f:
embed_weight = f.get_tensor(embed_key)
embed_layer = nn.Embedding.from_pretrained(embed_weight.to(MODEL_DTYPE))
@@ -6,17 +6,19 @@ import os
import openai # use the official client for correctness check
import pytest
import pytest_asyncio
from huggingface_hub import snapshot_download
from tests.conftest import AudioTestAssets
from tests.utils import RemoteOpenAIServer
from vllm.transformers_utils.repo_utils import hf_api
# NOTE - the tests in this module are currently analogous to test_chat, but are
# separated to avoid OOM killing due to module-scoped servers, since we
# need a multimodal model for these tests.
# Contains a modality specific lora alongside the base model
MULTIMODAL_MODEL_NAME = snapshot_download("microsoft/Phi-4-multimodal-instruct")
MULTIMODAL_MODEL_NAME = hf_api().snapshot_download(
"microsoft/Phi-4-multimodal-instruct"
)
AUDIO_LORA_PATH = os.path.join(MULTIMODAL_MODEL_NAME, "speech-lora")
ACTIVE_MM_LORA_RESPONSE = "Spoken text: The first words I spoke in the original chronograph, a little piece of practical poetry. Mary had a little lamb, it slept with quite a snow, and everywhere that Mary went, the lamb was sure to go." # noqa: E501