Flyte SGLang Plugin
Serve large language models using SGLang with Flyte Apps.
This plugin provides the SGLangAppEnvironment class for deploying and serving LLMs using SGLang.
Installation
pip install --pre flyteplugins-sglang
Usage
import flyte
import flyte.app
from flyteplugins.sglang import SGLangAppEnvironment
# Define the SGLang app environment
sglang_app = SGLangAppEnvironment(
name="my-llm-app",
model_path="s3://your-bucket/models/your-model",
model_id="your-model-id",
resources=flyte.Resources(cpu="4", memory="16Gi", gpu="L40s:1"),
stream_model=True, # Stream model directly from blob store to GPU
scaling=flyte.app.Scaling(
replicas=(0, 1),
scaledown_after=300,
),
)
if __name__ == "__main__":
flyte.init_from_config()
app = flyte.serve(sglang_app)
print(f"Deployed SGLang app: {app.url}")
Features
- Streaming Model Loading: Stream model weights directly from object storage to GPU memory, reducing startup time and disk requirements.
- OpenAI-Compatible API: The deployed app exposes an OpenAI-compatible API for chat completions.
- Auto-scaling: Configure scaling policies to scale up/down based on traffic.
- Tensor Parallelism: Support for distributed inference across multiple GPUs.
Extra Arguments
You can pass additional arguments to the SGLang server using the extra_args parameter:
sglang_app = SGLangAppEnvironment(
name="my-llm-app",
model_path="s3://your-bucket/models/your-model",
model_id="your-model-id",
extra_args="--context-length 8192",
)
See the SGLang server arguments documentation for available options.
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
No source distribution files available for this release.See tutorial on generating distribution archives.
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file flyteplugins_sglang-2.6.4-py3-none-any.whl.
File metadata
- Download URL: flyteplugins_sglang-2.6.4-py3-none-any.whl
- Upload date:
- Size: 8.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/7.0.0 CPython/3.13.15
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
5218f74227c4b764f35b1d0b45880a4b7a23c7f0a4cc786952bec9256686838a
|
|
| MD5 |
e807735e4c5effeea0d49e6a83c43da5
|
|
| BLAKE2b-256 |
5156266304be464c4f58729b7de275066011365793d699888b12d65e14be4f27
|
