A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 17, 04:15 UTC
docs: Add BentoML deployment doc (#3336)
Signed-off-by: Sherlock113 <sherlockxu07@gmail.com>
Sherlock Xu committed
Mar 13, 2024 at 01:34 UTC
b0925b38789bb3b20dcc39e229fcfe12a311e487
2 files changed
+9
docs/source/index.rst
+1
@@ -73,6 +73,7 @@ Documentation
73
serving/run_on_sky
74
serving/deploying_with_kserve
75
serving/deploying_with_triton
76
+ serving/deploying_with_bentoml
77
serving/deploying_with_docker
78
serving/serving_with_langchain
79
serving/metrics
docs/source/serving/deploying_with_bentoml.rst
new
+8
@@ -0,0 +1,8 @@
1
+.. _deploying_with_bentoml:
2
+
3
+Deploying with BentoML
4
+======================
5
+
6
+`BentoML <https://github.com/bentoml/BentoML>`_ allows you to deploy a large language model (LLM) server with vLLM as the backend, which exposes OpenAI-compatible endpoints. You can serve the model locally or containerize it as an OCI-complicant image and deploy it on Kubernetes.
7
+
8
+For details, see the tutorial `vLLM inference in the BentoML documentation <https://docs.bentoml.com/en/latest/use-cases/large-language-models/vllm.html>`_.
\ No newline at end of file