Instructions to use zai-org/GLM-5.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zai-org/GLM-5.3 with Transformers:

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

pipe = pipeline("text-generation", model="zai-org/GLM-5.3")
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("zai-org/GLM-5.3")
model = AutoModelForCausalLM.from_pretrained("zai-org/GLM-5.3", 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]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zai-org/GLM-5.3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zai-org/GLM-5.3"
# 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-5.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zai-org/GLM-5.3

SGLang

How to use zai-org/GLM-5.3 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-5.3" \
    --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-5.3",
		"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-5.3" \
        --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-5.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zai-org/GLM-5.3 with Docker Model Runner:
```
docker model run hf.co/zai-org/GLM-5.3
```

vMaroon commited on about 23 hours ago

Commit

ffc0d7c

verified ·

1 Parent(s): ad14a0a

chat template: pair tool results by sort-merge instead of list.index

Browse files

Files changed (1) hide show

chat_template.jinja +22 -11

chat_template.jinja CHANGED Viewed

@@ -209,20 +209,31 @@ For each function call, output the function name and arguments within the follow
         {%- endif -%}
     {%- endif -%}
     {%- if ns_chk.can_sort -%}
         {%- for tc_id in ns_chk.tcs -%}
-            {%- if tc_id in ns_chk.res -%}
-                {%- set p = ns_chk.res.index(tc_id) -%}
-                {%- set m = messages[ns_chk.mk[p]] -%}
-                {%- if ns_chk.ek[p] >= 0 -%}
-                    {%- set entry = m.content[ns_chk.ek[p]] -%}
-                    {%- if entry.output is iterable and entry.output is not string and entry.output is not mapping and entry.output and entry.output.0.type == "tool_reference" -%}
-                        {{- tool_references_to_response(entry.output) -}}
-                    {%- else -%}
-                        {{- tool_response(visible_text(entry.output)) -}}
-                    {%- endif -%}
                 {%- else -%}
-                    {{- render_tool_response(m) -}}
                 {%- endif -%}
             {%- endif -%}
         {%- endfor -%}
     {%- else -%}

         {%- endif -%}
     {%- endif -%}
     {%- if ns_chk.can_sort -%}
+        {%- set ns_ord = namespace(res=[], tcs=[], j=0, pairs=[]) -%}
+        {%- for eid in ns_chk.res -%}
+            {%- set ns_ord.res = ns_ord.res + [{'id': eid, 'p': loop.index0}] -%}
+        {%- endfor -%}
         {%- for tc_id in ns_chk.tcs -%}
+            {%- set ns_ord.tcs = ns_ord.tcs + [{'id': tc_id, 'i': loop.index0}] -%}
+        {%- endfor -%}
+        {%- set ns_ord.res = ns_ord.res | sort(attribute='id', case_sensitive=true) -%}
+        {%- for tc in ns_ord.tcs | sort(attribute='id', case_sensitive=true) -%}
+            {%- if ns_ord.j < ns_ord.res | length and ns_ord.res[ns_ord.j].id == tc.id -%}
+                {%- set ns_ord.pairs = ns_ord.pairs + [{'i': tc.i, 'p': ns_ord.res[ns_ord.j].p}] -%}
+                {%- set ns_ord.j = ns_ord.j + 1 -%}
+            {%- endif -%}
+        {%- endfor -%}
+        {%- for pair in ns_ord.pairs | sort(attribute='i') -%}
+            {%- set m = messages[ns_chk.mk[pair.p]] -%}
+            {%- if ns_chk.ek[pair.p] >= 0 -%}
+                {%- set entry = m.content[ns_chk.ek[pair.p]] -%}
+                {%- if entry.output is iterable and entry.output is not string and entry.output is not mapping and entry.output and entry.output.0.type == "tool_reference" -%}
+                    {{- tool_references_to_response(entry.output) -}}
                 {%- else -%}
+                    {{- tool_response(visible_text(entry.output)) -}}
                 {%- endif -%}
+            {%- else -%}
+                {{- render_tool_response(m) -}}
             {%- endif -%}
         {%- endfor -%}
     {%- else -%}