Instructions to use jdopensource/JoyAI-LLM-Flash-INT4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jdopensource/JoyAI-LLM-Flash-INT4 with Transformers:

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

pipe = pipeline("text-generation", model="jdopensource/JoyAI-LLM-Flash-INT4", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("jdopensource/JoyAI-LLM-Flash-INT4", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use jdopensource/JoyAI-LLM-Flash-INT4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jdopensource/JoyAI-LLM-Flash-INT4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jdopensource/JoyAI-LLM-Flash-INT4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jdopensource/JoyAI-LLM-Flash-INT4

SGLang

How to use jdopensource/JoyAI-LLM-Flash-INT4 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 "jdopensource/JoyAI-LLM-Flash-INT4" \
    --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": "jdopensource/JoyAI-LLM-Flash-INT4",
		"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 "jdopensource/JoyAI-LLM-Flash-INT4" \
        --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": "jdopensource/JoyAI-LLM-Flash-INT4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jdopensource/JoyAI-LLM-Flash-INT4 with Docker Model Runner:
```
docker model run hf.co/jdopensource/JoyAI-LLM-Flash-INT4
```

JoyAI-LLM-Flash-INT4 / docs /deploy_guidance.md

Mingke977

Update docs/deploy_guidance.md

dbad83f verified 3 months ago

preview code

raw

history blame contribute delete

1.71 kB

Model Deployment Guide

This guide offers a selection of deployment command examples for JoyAI-LLM Flash, which may not be the optimal configuration. Given the rapid evolution of inference engines, we recommend referring to their official documentation for the latest updates to ensure peak performance.

Support for JoyAI-LLM Flash’s dense MTP architecture is currently being integrated into vLLM and SGLang. Until these PRs are merged into a stable release, please use the nightly Docker image for access to these features.

vLLM Deployment

Here is the example to serve this model on a single GPU card via vLLM:

pull the Docker image.

docker pull jdopensource/joyai-llm-vllm:v0.15.1-joyai_llm_flash

launch JoyAI-LLM Flash model with dense MTP.

vllm serve jdopensource/JoyAI-LLM-Flash-INT4 -tp 1 --trust-remote-code \
   --tool-call-parser qwen3_coder --enable-auto-tool-choice \
   --speculative-config $'{"method": "mtp", "num_speculative_tokens": 3}'

Key notes

--tool-call-parser qwen3_coder: Required for enabling tool calling

SGLang Deployment

Similarly, here is the example to run on a single GPU card via SGLang:

pull the Docker image.

docker pull jdopensource/joyai-llm-sglang:v0.5.8-joyai_llm_flash

launch JoyAI-LLM Flash model with dense MTP.

python3 -m sglang.launch_server --model-path jdopensource/JoyAI-LLM-Flash-INT4 --tp-size 1 --trust-remote-code \
  --tool-call-parser qwen3_coder \
  --speculative-algorithm EAGLE \
  --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4

Key notes:

--tool-call-parser qwen3_coder: Required when enabling tool usage.