Difficulty deploying to Sagemaker AI
#65
by
josiahschuller
- opened
I have encountered some errors when I try to deploy this model to Sagemaker AI on AWS.
My code:
from sagemaker.huggingface import HuggingFaceModel, get_huggingface_llm_image_uri
env = {
"HF_MODEL_ID": "vikhyatk/moondream2",
"HF_TASK": "object-detection",
"HF_MODEL_REVISION": "2025-01-09",
"HF_MODEL_TRUST_REMOTE_CODE": "true",
}
huggingface_model = HuggingFaceModel(
env=env,
role="arn:aws:iam::171578333850:role/ai-cia-sagemaker-exec-role",
image_uri=get_huggingface_llm_image_uri(
backend="huggingface",
region="ap-southeast-2",
),
)
predictor = huggingface_model.deploy(
initial_instance_count=1,
instance_type="ml.g4dn.xlarge",
)
AWS CloudWatch errors:
#033[2m2025-03-21T05:16:02.283155Z#033[0m #033[31mERROR#033[0m #033[2mtext_generation_launcher#033[0m#033[2m:#033[0m Error when initializing model
Traceback (most recent call last):
File "/opt/conda/bin/text-generation-server", line 8, in <module>
sys.exit(app())
File "/opt/conda/lib/python3.11/site-packages/typer/main.py", line 321, in __call__
return get_command(self)(*args, **kwargs)
File "/opt/conda/lib/python3.11/site-packages/click/core.py", line 1157, in __call__
return self.main(*args, **kwargs)
File "/opt/conda/lib/python3.11/site-packages/typer/core.py", line 728, in main
return _main(
File "/opt/conda/lib/python3.11/site-packages/typer/core.py", line 197, in _main
rv = self.invoke(ctx)
File "/opt/conda/lib/python3.11/site-packages/click/core.py", line 1688, in invoke
return _process_result(sub_ctx.command.invoke(sub_ctx))
File "/opt/conda/lib/python3.11/site-packages/click/core.py", line 1434, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "/opt/conda/lib/python3.11/site-packages/click/core.py", line 783, in invoke
return __callback(*args, **kwargs)
File "/opt/conda/lib/python3.11/site-packages/typer/main.py", line 703, in wrapper
return callback(**use_params)
File "/opt/conda/lib/python3.11/site-packages/text_generation_server/cli.py", line 117, in serve
server.serve(
File "/opt/conda/lib/python3.11/site-packages/text_generation_server/server.py", line 315, in serve
asyncio.run(
File "/opt/conda/lib/python3.11/asyncio/runners.py", line 190, in run
return runner.run(main)
File "/opt/conda/lib/python3.11/asyncio/runners.py", line 118, in run
return self._loop.run_until_complete(task)
File "/opt/conda/lib/python3.11/asyncio/base_events.py", line 641, in run_until_complete
self.run_forever()
File "/opt/conda/lib/python3.11/asyncio/base_events.py", line 608, in run_forever
self._run_once()
File "/opt/conda/lib/python3.11/asyncio/base_events.py", line 1936, in _run_once
handle._run()
File "/opt/conda/lib/python3.11/asyncio/events.py", line 84, in _run
self._context.run(self._callback, *self._args)
> File "/opt/conda/lib/python3.11/site-packages/text_generation_server/server.py", line 268, in serve_inner
model = get_model_with_lora_adapters(
File "/opt/conda/lib/python3.11/site-packages/text_generation_server/models/__init__.py", line 1363, in get_model_with_lora_adapters
model = get_model(
File "/opt/conda/lib/python3.11/site-packages/text_generation_server/models/__init__.py", line 1326, in get_model
return CausalLM.fallback(
File "/opt/conda/lib/python3.11/site-packages/text_generation_server/models/causal_lm.py", line 619, in fallback
model = AutoModelForCausalLM.from_pretrained(
File "/opt/conda/lib/python3.11/site-packages/transformers/models/auto/auto_factory.py", line 526, in from_pretrained
config, kwargs = AutoConfig.from_pretrained(
File "/opt/conda/lib/python3.11/site-packages/transformers/models/auto/configuration_auto.py", line 1026, in from_pretrained
config_class = get_class_from_dynamic_module(
File "/opt/conda/lib/python3.11/site-packages/transformers/dynamic_module_utils.py", line 540, in get_class_from_dynamic_module
final_module = get_cached_module_file(
File "/opt/conda/lib/python3.11/site-packages/transformers/dynamic_module_utils.py", line 403, in get_cached_module_file
get_cached_module_file(
File "/opt/conda/lib/python3.11/site-packages/transformers/dynamic_module_utils.py", line 365, in get_cached_module_file
modules_needed = check_imports(resolved_module_file)
File "/opt/conda/lib/python3.11/site-packages/transformers/dynamic_module_utils.py", line 197, in check_imports
raise ImportError(
ImportError: This modeling file requires the following packages that were not found in your environment: pyvips. Run `pip install pyvips`
Can you try installing pyvips
and pyvips-binary
using pip?