Instructions to use QuantTrio/DeepSeek-V3.1-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantTrio/DeepSeek-V3.1-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="QuantTrio/DeepSeek-V3.1-AWQ", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("QuantTrio/DeepSeek-V3.1-AWQ", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("QuantTrio/DeepSeek-V3.1-AWQ", trust_remote_code=True, 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use QuantTrio/DeepSeek-V3.1-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuantTrio/DeepSeek-V3.1-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuantTrio/DeepSeek-V3.1-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QuantTrio/DeepSeek-V3.1-AWQ

SGLang

How to use QuantTrio/DeepSeek-V3.1-AWQ 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 "QuantTrio/DeepSeek-V3.1-AWQ" \
    --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": "QuantTrio/DeepSeek-V3.1-AWQ",
		"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 "QuantTrio/DeepSeek-V3.1-AWQ" \
        --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": "QuantTrio/DeepSeek-V3.1-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use QuantTrio/DeepSeek-V3.1-AWQ with Docker Model Runner:
```
docker model run hf.co/QuantTrio/DeepSeek-V3.1-AWQ
```

tclf90 commited on Aug 27, 2025

Commit

4e7ab3e

verified ·

1 Parent(s): e3ac9c8

new installation instuction for stable/correct performance

Browse files

Files changed (1) hide show

README.md +11 -4

README.md CHANGED Viewed

@@ -17,17 +17,18 @@ base_model_relation: quantized
 Base model: [DeepSeek-V3.1](https://huggingface.co/deepseek-ai/DeepSeek-V3.1)
 ### 【Dependencies / Installation】
-As of **2025-08-23**, create a fresh Python environment and run:
 ```bash
 # ❗there are glitches with vllm 0.10.1.1, still looking for resolutions❗
 # ❗downgrade vllm for now ❗
-pip install vllm==0.9.0
-pip install transformers==4.53
-# ❗patch up AWQ MoE quant config, otherwise some modules cannot be properly loaded❗
 SITE_PACKAGES=$(pip -V | awk '{print $4}' | sed 's/\/pip$//')
 cp awq_marlin.py "$SITE_PACKAGES/vllm/model_executor/layers/quantization/awq_marlin.py"
 ```
 ### 【vLLM Single Node with 8 GPUs — Startup Command】
@@ -51,6 +52,12 @@ vllm serve \
 ### 【Logs】
 ```
 2025-08-23
 1. Initial commit
 ```

 Base model: [DeepSeek-V3.1](https://huggingface.co/deepseek-ai/DeepSeek-V3.1)
 ### 【Dependencies / Installation】
+As of **2025-08-27**, create a fresh Python environment and run:
 ```bash
 # ❗there are glitches with vllm 0.10.1.1, still looking for resolutions❗
 # ❗downgrade vllm for now ❗
+pip install vllm==0.9.2 transformers==4.53.0
 SITE_PACKAGES=$(pip -V | awk '{print $4}' | sed 's/\/pip$//')
+# ❗patch up AWQ MoE quant config, otherwise some modules cannot be properly loaded❗
 cp awq_marlin.py "$SITE_PACKAGES/vllm/model_executor/layers/quantization/awq_marlin.py"
+# ❗patch up for fp32 e_score_correction_bias, see https://www.github.com/vllm-project/vllm/pull/23640❗
+cp deepseek_v2.py "$SITE_PACKAGES/vllm/model_executor/models/deepseek_v2.py"
 ```
 ### 【vLLM Single Node with 8 GPUs — Startup Command】
 ### 【Logs】
 ```
+2025-08-27
+1. new installation instuction for stable/correct performance
+  (a) use vllm 0.9.2 instead of 0.9.0:
+      there is unidentified issue with 0.9.0 🥹 which causes numerical error
+  (b) patch up deepseek_v2.py for fp32 e_score_correction_bias
 2025-08-23
 1. Initial commit
 ```