Instructions to use kodelow/Hy3-NVFP4-W4A16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kodelow/Hy3-NVFP4-W4A16 with Transformers:

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

pipe = pipeline("text-generation", model="kodelow/Hy3-NVFP4-W4A16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kodelow/Hy3-NVFP4-W4A16")
model = AutoModelForCausalLM.from_pretrained("kodelow/Hy3-NVFP4-W4A16")
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 Settings

vLLM

How to use kodelow/Hy3-NVFP4-W4A16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kodelow/Hy3-NVFP4-W4A16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kodelow/Hy3-NVFP4-W4A16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kodelow/Hy3-NVFP4-W4A16

SGLang

How to use kodelow/Hy3-NVFP4-W4A16 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 "kodelow/Hy3-NVFP4-W4A16" \
    --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": "kodelow/Hy3-NVFP4-W4A16",
		"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 "kodelow/Hy3-NVFP4-W4A16" \
        --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": "kodelow/Hy3-NVFP4-W4A16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kodelow/Hy3-NVFP4-W4A16 with Docker Model Runner:
```
docker model run hf.co/kodelow/Hy3-NVFP4-W4A16
```

olka-fi commited on 7 days ago

Commit

9a89092

verified ·

1 Parent(s): 26b87c8

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -6

README.md CHANGED Viewed

@@ -31,12 +31,7 @@ are quantized to 4-bit; everything quality-sensitive stays BF16.
 > backends (`flashinfer_trtllm` / `cutlass` / `cutedsl`) are **W4A4** and *reject a
 > weight-only scheme* — `--moe-backend flashinfer_trtllm` fails with
 > `kernel does not support QuantKey(u8, scale(f8e4m3))`, so vLLM auto-selects MARLIN.
->
-> **Consequence:** measured **~26% slower** than the MXFP4 sibling with MTP
-> (**674 vs 849 tok/s**, aggregate at concurrency 16 on one B300). If throughput
-> matters, prefer [**`olka-fi/Hy3-MXFP4`**](https://huggingface.co/olka-fi/Hy3-MXFP4),
-> which runs on the standard MXFP4 path. A FlashInfer-capable W4A4 variant needs
-> activation calibration (planned separately — see [below](#serving-with-vllm)).
 | | |
 |---|---|

 > backends (`flashinfer_trtllm` / `cutlass` / `cutedsl`) are **W4A4** and *reject a
 > weight-only scheme* — `--moe-backend flashinfer_trtllm` fails with
 > `kernel does not support QuantKey(u8, scale(f8e4m3))`, so vLLM auto-selects MARLIN.
 | | |
 |---|---|