Files
xc-llm-ascend/tools/send_mm_request.py

46 lines
1.3 KiB
Python
Raw Permalink Normal View History

import base64
import os
[CI][Misc] Use offline mode for model downloads (#7179) ### What this PR does / why we need it? 1. For all parts of the current test module involving the millisecond download model, add the `local_file_only` parameter to specify offline mode; this ensures that CI will not fail due to network instability. 2. Install modelscope from a fixed commit until it next release ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? check if the env or arg `local_files_only` works 1) set the env: ```shell export HF_HUB_OFFLINE=1 ``` 2) run the script ```python from transformers import PretrainedConfig import huggingface_hub from modelscope.utils.hf_util import patch_hub patch_hub() model="Qwen/Qwen3-0.6B" kwargs = {} config_dict, _ = PretrainedConfig.get_config_dict( model, trust_remote_code=True, local_files_only=huggingface_hub.constants.HF_HUB_OFFLINE, **kwargs, ) print(config_dict) ``` it works well: ```shell 2026-03-06 06:40:12,546 - modelscope - WARNING - We can not confirm the cached file is for revision: master The argument `trust_remote_code` is to be used with Auto classes. It has no effect here and is ignored. {'architectures': ['Qwen3ForCausalLM'], 'attention_bias': False, 'attention_dropout': 0.0, 'bos_token_id': 151643, 'eos_token_id': 151645, 'head_dim': 128, 'hidden_act': 'silu', 'hidden_size': 1024, 'initializer_range': 0.02, 'intermediate_size': 3072, 'max_position_embeddings': 40960, 'max_window_layers': 28, 'model_type': 'qwen3', 'num_attention_heads': 16, 'num_hidden_layers': 28, 'num_key_value_heads': 8, 'rms_norm_eps': 1e-06, 'rope_scaling': None, 'rope_theta': 1000000, 'sliding_window': None, 'tie_word_embeddings': True, 'torch_dtype': 'bfloat16', 'transformers_version': '4.51.0', 'use_cache': True, 'use_sliding_window': False, 'vocab_size': 151936, '_commit_hash': None} ``` 3) test the model repo does not cached locally when the env `HF_HUB_OFFLINE`==True ```python from transformers import PretrainedConfig import huggingface_hub from modelscope.utils.hf_util import patch_hub patch_hub() model="FireRedTeam/FireRed-OCR" kwargs = {} config_dict, _ = PretrainedConfig.get_config_dict( model, trust_remote_code=True, local_files_only=huggingface_hub.constants.HF_HUB_OFFLINE, **kwargs, ) print(config_dict) ``` and the result is as expected: ```shell File "/workspace/demo.py", line 12, in <module> config_dict, _ = PretrainedConfig.get_config_dict( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/python3.11.14/lib/python3.11/site-packages/modelscope/utils/hf_util/patcher.py", line 189, in patch_get_config_dict model_dir = get_model_dir(pretrained_model_name_or_path, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/python3.11.14/lib/python3.11/site-packages/modelscope/utils/hf_util/patcher.py", line 164, in get_model_dir model_dir = snapshot_download( ^^^^^^^^^^^^^^^^^^ File "/usr/local/python3.11.14/lib/python3.11/site-packages/modelscope/hub/snapshot_download.py", line 137, in snapshot_download return _snapshot_download( ^^^^^^^^^^^^^^^^^^^ File "/usr/local/python3.11.14/lib/python3.11/site-packages/modelscope/hub/snapshot_download.py", line 283, in _snapshot_download raise ValueError( ValueError: Cannot find the requested files in the cached path and outgoing traffic has been disabled. To enable look-ups and downloads online, set 'local_files_only' to False ``` - vLLM version: v0.16.0 - vLLM main: https://github.com/vllm-project/vllm/commit/15d76f74e2fdb12a95ea00f0ca283acf6219a2b7 --------- Signed-off-by: wangli <wangli858794774@gmail.com>
2026-03-13 08:52:24 +08:00
import huggingface_hub
import requests
from modelscope import snapshot_download # type: ignore
[CI][Misc] Use offline mode for model downloads (#7179) ### What this PR does / why we need it? 1. For all parts of the current test module involving the millisecond download model, add the `local_file_only` parameter to specify offline mode; this ensures that CI will not fail due to network instability. 2. Install modelscope from a fixed commit until it next release ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? check if the env or arg `local_files_only` works 1) set the env: ```shell export HF_HUB_OFFLINE=1 ``` 2) run the script ```python from transformers import PretrainedConfig import huggingface_hub from modelscope.utils.hf_util import patch_hub patch_hub() model="Qwen/Qwen3-0.6B" kwargs = {} config_dict, _ = PretrainedConfig.get_config_dict( model, trust_remote_code=True, local_files_only=huggingface_hub.constants.HF_HUB_OFFLINE, **kwargs, ) print(config_dict) ``` it works well: ```shell 2026-03-06 06:40:12,546 - modelscope - WARNING - We can not confirm the cached file is for revision: master The argument `trust_remote_code` is to be used with Auto classes. It has no effect here and is ignored. {'architectures': ['Qwen3ForCausalLM'], 'attention_bias': False, 'attention_dropout': 0.0, 'bos_token_id': 151643, 'eos_token_id': 151645, 'head_dim': 128, 'hidden_act': 'silu', 'hidden_size': 1024, 'initializer_range': 0.02, 'intermediate_size': 3072, 'max_position_embeddings': 40960, 'max_window_layers': 28, 'model_type': 'qwen3', 'num_attention_heads': 16, 'num_hidden_layers': 28, 'num_key_value_heads': 8, 'rms_norm_eps': 1e-06, 'rope_scaling': None, 'rope_theta': 1000000, 'sliding_window': None, 'tie_word_embeddings': True, 'torch_dtype': 'bfloat16', 'transformers_version': '4.51.0', 'use_cache': True, 'use_sliding_window': False, 'vocab_size': 151936, '_commit_hash': None} ``` 3) test the model repo does not cached locally when the env `HF_HUB_OFFLINE`==True ```python from transformers import PretrainedConfig import huggingface_hub from modelscope.utils.hf_util import patch_hub patch_hub() model="FireRedTeam/FireRed-OCR" kwargs = {} config_dict, _ = PretrainedConfig.get_config_dict( model, trust_remote_code=True, local_files_only=huggingface_hub.constants.HF_HUB_OFFLINE, **kwargs, ) print(config_dict) ``` and the result is as expected: ```shell File "/workspace/demo.py", line 12, in <module> config_dict, _ = PretrainedConfig.get_config_dict( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/python3.11.14/lib/python3.11/site-packages/modelscope/utils/hf_util/patcher.py", line 189, in patch_get_config_dict model_dir = get_model_dir(pretrained_model_name_or_path, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/python3.11.14/lib/python3.11/site-packages/modelscope/utils/hf_util/patcher.py", line 164, in get_model_dir model_dir = snapshot_download( ^^^^^^^^^^^^^^^^^^ File "/usr/local/python3.11.14/lib/python3.11/site-packages/modelscope/hub/snapshot_download.py", line 137, in snapshot_download return _snapshot_download( ^^^^^^^^^^^^^^^^^^^ File "/usr/local/python3.11.14/lib/python3.11/site-packages/modelscope/hub/snapshot_download.py", line 283, in _snapshot_download raise ValueError( ValueError: Cannot find the requested files in the cached path and outgoing traffic has been disabled. To enable look-ups and downloads online, set 'local_files_only' to False ``` - vLLM version: v0.16.0 - vLLM main: https://github.com/vllm-project/vllm/commit/15d76f74e2fdb12a95ea00f0ca283acf6219a2b7 --------- Signed-off-by: wangli <wangli858794774@gmail.com>
2026-03-13 08:52:24 +08:00
mm_dir = snapshot_download(
"vllm-ascend/mm_request",
repo_type="dataset",
local_files_only=huggingface_hub.constants.HF_HUB_OFFLINE,
)
image_path = os.path.join(mm_dir, "test_mm2.jpg")
with open(image_path, "rb") as image_file:
image_data = base64.b64encode(image_file.read()).decode("utf-8")
data = {
"messages": [
{
"role": "user",
"content": [
{"type": "text", "text": "What is the content of this image?"},
{"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{image_data}"}},
],
}
],
"eos_token_id": [1, 106],
"pad_token_id": 0,
"top_k": 64,
"top_p": 0.95,
"max_tokens": 8192,
"stream": False,
}
headers = {"Accept": "application/json", "Content-Type": "application/json"}
def send_image_request(model, server):
data["model"] = model
url = server.url_for("v1", "chat", "completions")
response = requests.post(url, headers=headers, json=data)
print("Status Code:", response.status_code)
response_json = response.json()
print("Response:", response_json)
assert response_json["choices"][0]["message"]["content"], "empty response"