Instructions to use Infermatic/Llama-3.3-70B-Instruct-FP8-Dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Infermatic/Llama-3.3-70B-Instruct-FP8-Dynamic with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Infermatic/Llama-3.3-70B-Instruct-FP8-Dynamic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Infermatic/Llama-3.3-70B-Instruct-FP8-Dynamic")
model = AutoModelForCausalLM.from_pretrained("Infermatic/Llama-3.3-70B-Instruct-FP8-Dynamic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Infermatic/Llama-3.3-70B-Instruct-FP8-Dynamic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Infermatic/Llama-3.3-70B-Instruct-FP8-Dynamic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Infermatic/Llama-3.3-70B-Instruct-FP8-Dynamic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Infermatic/Llama-3.3-70B-Instruct-FP8-Dynamic

SGLang

How to use Infermatic/Llama-3.3-70B-Instruct-FP8-Dynamic with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Infermatic/Llama-3.3-70B-Instruct-FP8-Dynamic" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Infermatic/Llama-3.3-70B-Instruct-FP8-Dynamic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Infermatic/Llama-3.3-70B-Instruct-FP8-Dynamic" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Infermatic/Llama-3.3-70B-Instruct-FP8-Dynamic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Infermatic/Llama-3.3-70B-Instruct-FP8-Dynamic with Docker Model Runner:
```
docker model run hf.co/Infermatic/Llama-3.3-70B-Instruct-FP8-Dynamic
```

How to serve this fp8 model in vllm?

by U2hhd24 - opened Dec 27, 2024

Discussion

U2hhd24

Dec 27, 2024

Hi,

I tried to serve this model with vllm:0.6.5 but it failed, what should I do to serve this model?

my docker-compose.yaml

  vllm:
    <<: *common-config
    image: vllm/vllm-openai:v0.6.5
    container_name: vllm
    ports:
      - "8001:8000"
    volumes:
      - /mnt:/mnt
    command: >
      --model /mnt/models/meta-llama/llama-3.3-70b-instruct-fp8-dynamic
      --gpu-memory-utilization 0.98
      --enforce_eager
      --max-model-len 2048

Error message

Process SpawnProcess-1:
Traceback (most recent call last):
  File "/usr/lib/python3.12/multiprocessing/process.py", line 314, in _bootstrap
    self.run()
  File "/usr/lib/python3.12/multiprocessing/process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "/usr/local/lib/python3.12/dist-packages/vllm/engine/multiprocessing/engine.py", line 368, in run_mp_engine
    raise e
  File "/usr/local/lib/python3.12/dist-packages/vllm/engine/multiprocessing/engine.py", line 357, in run_mp_engine
    engine = MQLLMEngine.from_engine_args(engine_args=engine_args,
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/vllm/engine/multiprocessing/engine.py", line 119, in from_engine_args
    return cls(ipc_path=ipc_path,
           ^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/vllm/engine/multiprocessing/engine.py", line 71, in __init__
    self.engine = LLMEngine(*args, **kwargs)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/vllm/engine/llm_engine.py", line 288, in __init__
    self.model_executor = executor_class(vllm_config=vllm_config, )
                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/vllm/executor/executor_base.py", line 36, in __init__
    self._init_executor()
  File "/usr/local/lib/python3.12/dist-packages/vllm/executor/gpu_executor.py", line 34, in _init_executor
    self.driver_worker.init_device()
  File "/usr/local/lib/python3.12/dist-packages/vllm/worker/worker.py", line 138, in init_device
    torch.cuda.set_device(self.device)
  File "/usr/local/lib/python3.12/dist-packages/torch/cuda/__init__.py", line 478, in set_device
    torch._C._cuda_setDevice(device)
  File "/usr/local/lib/python3.12/dist-packages/torch/cuda/__init__.py", line 319, in _lazy_init
    torch._C._cuda_init()
RuntimeError: Unexpected error from cudaGetDeviceCount(). Did you run some cuda functions before calling NumCudaDevices() that might have already set an error? Error 802: system not yet initialized
Traceback (most recent call last):
  File "<frozen runpy>", line 198, in _run_module_as_main
  File "<frozen runpy>", line 88, in _run_code
  File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py", line 709, in <module>
    uvloop.run(run_server(args))
  File "/usr/local/lib/python3.12/dist-packages/uvloop/__init__.py", line 109, in run
    return __asyncio.run(
           ^^^^^^^^^^^^^^
  File "/usr/lib/python3.12/asyncio/runners.py", line 194, in run
    return runner.run(main)
           ^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.12/asyncio/runners.py", line 118, in run
    return self._loop.run_until_complete(task)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete
  File "/usr/local/lib/python3.12/dist-packages/uvloop/__init__.py", line 61, in wrapper
    return await main
           ^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py", line 675, in run_server
    async with build_async_engine_client(args) as engine_client:
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.12/contextlib.py", line 210, in __aenter__
    return await anext(self.gen)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py", line 118, in build_async_engine_client
    async with build_async_engine_client_from_engine_args(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.12/contextlib.py", line 210, in __aenter__
    return await anext(self.gen)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py", line 223, in build_async_engine_client_from_engine_args
    raise RuntimeError(
RuntimeError: Engine process failed to start. See stack trace for the root cause.

Svak

Infermatic AI org Dec 27, 2024

Try with the .2 version instead of .5

vllm/vllm-openai:v0.6.2, it should work with your current command

U2hhd24

Dec 31, 2024

•

edited Dec 31, 2024

I tried with 0.6.x and 0.5.x and all of them not working

Svak

Infermatic AI org Dec 31, 2024

docker run -d --name llama --runtime nvidia --gpus all -p 8099:8000 --shm-size=10.24gb vllm/vllm-openai:v0.6.2 --model Infermatic/Llama-3.3-70B-Instruct-FP8-Dynamic --tensor-parallel-size 2 --gpu-memory-utilization 0.95 --max-model-len 32768

Try with this command

Svak changed discussion status to closed Dec 31, 2024

Svak changed discussion status to open Dec 31, 2024

U2hhd24

Jan 1, 2025

Thank you! It works!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment