Instructions to use inference-optimization/GLM-4.7-Flash-0.82B-MTP-FP8-Dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inference-optimization/GLM-4.7-Flash-0.82B-MTP-FP8-Dynamic with Transformers:

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

pipe = pipeline("text-generation", model="inference-optimization/GLM-4.7-Flash-0.82B-MTP-FP8-Dynamic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("inference-optimization/GLM-4.7-Flash-0.82B-MTP-FP8-Dynamic")
model = AutoModelForCausalLM.from_pretrained("inference-optimization/GLM-4.7-Flash-0.82B-MTP-FP8-Dynamic", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use inference-optimization/GLM-4.7-Flash-0.82B-MTP-FP8-Dynamic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "inference-optimization/GLM-4.7-Flash-0.82B-MTP-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": "inference-optimization/GLM-4.7-Flash-0.82B-MTP-FP8-Dynamic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/inference-optimization/GLM-4.7-Flash-0.82B-MTP-FP8-Dynamic

SGLang

How to use inference-optimization/GLM-4.7-Flash-0.82B-MTP-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 "inference-optimization/GLM-4.7-Flash-0.82B-MTP-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": "inference-optimization/GLM-4.7-Flash-0.82B-MTP-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 "inference-optimization/GLM-4.7-Flash-0.82B-MTP-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": "inference-optimization/GLM-4.7-Flash-0.82B-MTP-FP8-Dynamic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use inference-optimization/GLM-4.7-Flash-0.82B-MTP-FP8-Dynamic with Docker Model Runner:
```
docker model run hf.co/inference-optimization/GLM-4.7-Flash-0.82B-MTP-FP8-Dynamic
```

GLM-4.7-Flash-0.82B-MTP-FP8-Dynamic

FP8_DYNAMIC version of inference-optimization/GLM-4.7-Flash-0.82B-MTP.

Quantization recipe

Uses Transformers 5.17.0 and LLM Compressor PR #3225.

import torch
from compressed_tensors.offload import set_onload_device
from compressed_tensors.quantization import preset_name_to_scheme
from transformers import AutoTokenizer, Glm4MoeLiteForCausalLM

from llmcompressor import oneshot
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.utils import load_context

MODEL_ID = "inference-optimization/GLM-4.7-Flash-0.82B-MTP"
SAVE_DIR = "GLM-4.7-Flash-0.82B-MTP-FP8-Dynamic"

with load_context(Glm4MoeLiteForCausalLM, load_mtp=True):
    model = Glm4MoeLiteForCausalLM.from_pretrained(
        MODEL_ID, dtype=torch.bfloat16, device_map="cpu",
    )
set_onload_device(model, "cuda")

recipe = QuantizationModifier(
    config_groups={
        "mtp": preset_name_to_scheme("FP8_DYNAMIC", targets=[r"re:^mtp\.layers\."]),
        "backbone": preset_name_to_scheme("FP8_DYNAMIC", targets=["Linear"]),
    },
    ignore=["lm_head", r"re:.*\.eh_proj$", r"re:.*\.indexer\..*"],
)

oneshot(model=model, recipe=recipe)
model.save_pretrained(SAVE_DIR)
AutoTokenizer.from_pretrained(MODEL_ID).save_pretrained(SAVE_DIR)