Instructions to use zai-org/GLM-4.7-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zai-org/GLM-4.7-Flash with Transformers:

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

pipe = pipeline("text-generation", model="zai-org/GLM-4.7-Flash")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zai-org/GLM-4.7-Flash")
model = AutoModelForCausalLM.from_pretrained("zai-org/GLM-4.7-Flash")
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]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use zai-org/GLM-4.7-Flash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zai-org/GLM-4.7-Flash"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zai-org/GLM-4.7-Flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zai-org/GLM-4.7-Flash

SGLang

How to use zai-org/GLM-4.7-Flash 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 "zai-org/GLM-4.7-Flash" \
    --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": "zai-org/GLM-4.7-Flash",
		"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 "zai-org/GLM-4.7-Flash" \
        --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": "zai-org/GLM-4.7-Flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zai-org/GLM-4.7-Flash with Docker Model Runner:
```
docker model run hf.co/zai-org/GLM-4.7-Flash
```

llama.cpp inference - 20 times (!) slower than OSS 20 on a RTX 5090

#12

by cmp-nct - opened Jan 19

Discussion

cmp-nct

Jan 19

Is llama.cpp inference properly supported ?
I ran a test on a 5090, using the Q4 model.

GPT-OSS-20B (also A3B) would provide anything from 200-400 token generation speed.
GLM-4.7-flash runs at only 40tk/sec without context and at 15k context it drops to below 10 tokens/sec.

ddh0

Jan 19

It is not yet supported in llama.cpp, but will be very soon, watch: https://github.com/ggml-org/llama.cpp/pull/18936

cmp-nct

Jan 19

@ddh0
I can see you are quite far already, nice !
Did you get good prefill and generation token speeds in your preliminary work already?
My hopes are high to have something qualitatively better than GPT-OSS (which runs also at 3B activated) while having similar performance.

ddh0

Jan 19

Yes the speed is great as expected, comparable to a 8B dense model I would say?

theo77186

Jan 19

Did you force enable flash attention? Because if that's the case, llama.cpp doesn't support flash attention with this model (at least with CUDA) and performance will tank a lot as attention will be computed on the CPU.

cmp-nct

Jan 19

•

edited Jan 19

You are right theo.
Speed is better now, but still severe degradation.
It starts at 140 (OSS would be 350-400), at 4000 tokens it's down to 105 already, at 15k context the speed is only around 50 remaining.

owao

Jan 19

•

edited Jan 19

It starts at 140 (OSS would be 350-400), at 4000 tokens it's down to 105 already, at 15k context the speed is only around 50 remaining.

I confirm

ddh0

Jan 20

Relevant llama.cpp thread (please don't crowd the thread with comments, I'm just putting it here so people can follow along with the progress): https://github.com/ggml-org/llama.cpp/issues/18944

JLouisBiz

Jan 20

I got 97 tokens on RTX 3090 and llama.cpp is updated, and it worked yesterday same for me.

ngxson

Jan 20

More optimizations are coming:

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