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

Libraries

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

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

pipe = pipeline("text-generation", model="jdopensource/JoyAI-LLM-Flash", 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", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Use Docker

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

SGLang

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

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

JoyAI-LLM-Flash / docs /deploy_guidance.md

Mingke977

Update docs/deploy_guidance.md

f4526ac verified 3 months ago

preview code

raw

history blame contribute delete

2.31 kB

	# JoyAI-LLM Flash Deployment Guide

	> [!Note]
	> 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 H200 single node via vLLM:

	1. pull the Docker image.
	```bash
	docker pull jdopensource/joyai-llm-vllm:v0.15.1-joyai_llm_flash
	```
	2. launch JoyAI-LLM Flash model with dense MTP.
	```bash
	# TP1 for memory efficiency
	vllm serve ${MODEL_PATH} -tp 1 --trust-remote-code \
	--tool-call-parser qwen3_coder --enable-auto-tool-choice \
	--speculative-config $'{"method": "mtp", "num_speculative_tokens": 3}'

	# TP8 for extreme speed and long context
	vllm serve ${MODEL_PATH} -tp 8 --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 H200 single node via SGLang:

	1. pull the Docker image.
	```bash
	docker pull jdopensource/joyai-llm-sglang:v0.5.8-joyai_llm_flash
	```
	2. launch JoyAI-LLM Flash model with dense MTP.

	```bash
	# TP1 for memory efficiency
	python3 -m sglang.launch_server --model-path ${MODEL_PATH} --tp-size 1 --trust-remote-code \
	--tool-call-parser qwen3_coder \
	--speculative-algorithm EAGLE --speculative-draft-model-path ${MTP_MODEL_PATH} \
	--speculative-num-steps 2 --speculative-eagle-topk 2 --speculative-num-draft-tokens 3

	# TP8 for extreme speed and long context
	python3 -m sglang.launch_server --model-path ${MODEL_PATH} --tp-size 8 --trust-remote-code \
	--tool-call-parser qwen3_coder \
	--speculative-algorithm EAGLE \
	--speculative-num-steps 2 --speculative-eagle-topk 2 --speculative-num-draft-tokens 3
	```
	Key notes:
	- `--tool-call-parser qwen3_coder`: Required when enabling tool usage.