Skip to content

GitLab

"csrc/vscode:/vscode.git/clone" did not exist on "d081da0064b5cda9e344f0fd519d67523a437a39"
Unverified Commit a1fe24d9 authored by Harry Mellor's avatar Harry Mellor Committed by GitHub
Browse files

Migrate docs from Sphinx to MkDocs (#18145) 


Signed-off-by: default avatarHarry Mellor <19981378+hmellor@users.noreply.github.com>
parent d0bc2f81
Show whitespace changes
Inline Side-by-side
Showing with 306 additions and 106 deletions
docs/source/contributing/profiling/profiling_index.md → docs/contributing/profiling.md
View file @ a1fe24d9
# Profiling vLLM
:::{warning}
Profiling is only intended for vLLM developers and maintainers to understand the proportion of time spent in different parts of the codebase. **vLLM end-users should never turn on profiling** as it will significantly slow down the inference.
:::
!!! warning
Profiling is only intended for vLLM developers and maintainers to understand the proportion of time spent in different parts of the codebase. **vLLM end-users should never turn on profiling** as it will significantly slow down the inference.
## Profile with PyTorch Profiler
......@@ -14,15 +13,13 @@ When using `benchmarks/benchmark_serving.py`, you can enable profiling by passin
Traces can be visualized using <https://ui.perfetto.dev/>.
:::{tip}
Only send a few requests through vLLM when profiling, as the traces can get quite large. Also, no need to untar the traces, they can be viewed directly.
:::
!!! tip
Only send a few requests through vLLM when profiling, as the traces can get quite large. Also, no need to untar the traces, they can be viewed directly.
:::{tip}
To stop the profiler - it flushes out all the profile trace files to the directory. This takes time, for example for about 100 requests worth of data for a llama 70b, it takes about 10 minutes to flush out on a H100.
Set the env variable VLLM_RPC_TIMEOUT to a big number before you start the server. Say something like 30 minutes.
`export VLLM_RPC_TIMEOUT=1800000`
:::
!!! tip
To stop the profiler - it flushes out all the profile trace files to the directory. This takes time, for example for about 100 requests worth of data for a llama 70b, it takes about 10 minutes to flush out on a H100.
Set the env variable VLLM_RPC_TIMEOUT to a big number before you start the server. Say something like 30 minutes.
`export VLLM_RPC_TIMEOUT=1800000`
### Example commands and usage
......
docs/source/deployment/docker.md → docs/deployment/docker.md
View file @ a1fe24d9
(deployment-docker)=
---
title: Using Docker
---
[](){ #deployment-docker }
# Using Docker
(deployment-docker-pre-built-image)=
[](){ #deployment-docker-pre-built-image }
## Use vLLM's Official Docker Image
......@@ -31,45 +32,40 @@ $ podman run --gpus all \
--model mistralai/Mistral-7B-v0.1
```
You can add any other <project:#engine-args> you need after the image tag (`vllm/vllm-openai:latest`).
:::{note}
You can either use the `ipc=host` flag or `--shm-size` flag to allow the
container to access the host's shared memory. vLLM uses PyTorch, which uses shared
memory to share data between processes under the hood, particularly for tensor parallel inference.
:::
You can add any other [engine-args][engine-args] you need after the image tag (`vllm/vllm-openai:latest`).
:::{note}
Optional dependencies are not included in order to avoid licensing issues (e.g. <gh-issue:8030>).
!!! note
You can either use the `ipc=host` flag or `--shm-size` flag to allow the
container to access the host's shared memory. vLLM uses PyTorch, which uses shared
memory to share data between processes under the hood, particularly for tensor parallel inference.
If you need to use those dependencies (having accepted the license terms),
create a custom Dockerfile on top of the base image with an extra layer that installs them:
!!! note
Optional dependencies are not included in order to avoid licensing issues (e.g. <gh-issue:8030>).
```Dockerfile
FROM vllm/vllm-openai:v0.8.3
If you need to use those dependencies (having accepted the license terms),
create a custom Dockerfile on top of the base image with an extra layer that installs them:
# e.g. install the `audio` optional dependencies
# NOTE: Make sure the version of vLLM matches the base image!
RUN uv pip install --system vllm[audio]==0.8.3
```
```Dockerfile
FROM vllm/vllm-openai:v0.8.3
:::
# e.g. install the `audio` optional dependencies
# NOTE: Make sure the version of vLLM matches the base image!
RUN uv pip install --system vllm[audio]==0.8.3
```
:::{tip}
Some new models may only be available on the main branch of [HF Transformers](https://github.com/huggingface/transformers).
!!! tip
Some new models may only be available on the main branch of [HF Transformers](https://github.com/huggingface/transformers).
To use the development version of `transformers`, create a custom Dockerfile on top of the base image
with an extra layer that installs their code from source:
To use the development version of `transformers`, create a custom Dockerfile on top of the base image
with an extra layer that installs their code from source:
```Dockerfile
FROM vllm/vllm-openai:latest
RUN uv pip install --system git+https://github.com/huggingface/transformers.git
```
```Dockerfile
FROM vllm/vllm-openai:latest
:::
RUN uv pip install --system git+https://github.com/huggingface/transformers.git
```
(deployment-docker-build-image-from-source)=
[](){ #deployment-docker-build-image-from-source }
## Building vLLM's Docker Image from Source
......@@ -80,25 +76,23 @@ You can build and run vLLM from source via the provided <gh-file:docker/Dockerfi
DOCKER_BUILDKIT=1 docker build . --target vllm-openai --tag vllm/vllm-openai --file docker/Dockerfile
```
:::{note}
By default vLLM will build for all GPU types for widest distribution. If you are just building for the
current GPU type the machine is running on, you can add the argument `--build-arg torch_cuda_arch_list=""`
for vLLM to find the current GPU type and build for that.
!!! note
By default vLLM will build for all GPU types for widest distribution. If you are just building for the
current GPU type the machine is running on, you can add the argument `--build-arg torch_cuda_arch_list=""`
for vLLM to find the current GPU type and build for that.
If you are using Podman instead of Docker, you might need to disable SELinux labeling by
adding `--security-opt label=disable` when running `podman build` command to avoid certain [existing issues](https://github.com/containers/buildah/discussions/4184).
:::
If you are using Podman instead of Docker, you might need to disable SELinux labeling by
adding `--security-opt label=disable` when running `podman build` command to avoid certain [existing issues](https://github.com/containers/buildah/discussions/4184).
## Building for Arm64/aarch64
A docker container can be built for aarch64 systems such as the Nvidia Grace-Hopper. At time of this writing, this requires the use
of PyTorch Nightly and should be considered **experimental**. Using the flag `--platform "linux/arm64"` will attempt to build for arm64.
:::{note}
Multiple modules must be compiled, so this process can take a while. Recommend using `--build-arg max_jobs=` & `--build-arg nvcc_threads=`
flags to speed up build process. However, ensure your `max_jobs` is substantially larger than `nvcc_threads` to get the most benefits.
Keep an eye on memory usage with parallel jobs as it can be substantial (see example below).
:::
!!! note
Multiple modules must be compiled, so this process can take a while. Recommend using `--build-arg max_jobs=` & `--build-arg nvcc_threads=`
flags to speed up build process. However, ensure your `max_jobs` is substantially larger than `nvcc_threads` to get the most benefits.
Keep an eye on memory usage with parallel jobs as it can be substantial (see example below).
```console
# Example of building on Nvidia GH200 server. (Memory usage: ~15GB, Build time: ~1475s / ~25 min, Image size: 6.93GB)
......@@ -128,6 +122,5 @@ $ docker run --runtime nvidia --gpus all \
The argument `vllm/vllm-openai` specifies the image to run, and should be replaced with the name of the custom-built image (the `-t` tag from the build command).
:::{note}
**For version 0.4.1 and 0.4.2 only** - the vLLM docker images under these versions are supposed to be run under the root user since a library under the root user's home directory, i.e. `/root/.config/vllm/nccl/cu12/libnccl.so.2.18.1` is required to be loaded during runtime. If you are running the container under a different user, you may need to first change the permissions of the library (and all the parent directories) to allow the user to access it, then run vLLM with environment variable `VLLM_NCCL_SO_PATH=/root/.config/vllm/nccl/cu12/libnccl.so.2.18.1` .
:::
!!! note
**For version 0.4.1 and 0.4.2 only** - the vLLM docker images under these versions are supposed to be run under the root user since a library under the root user's home directory, i.e. `/root/.config/vllm/nccl/cu12/libnccl.so.2.18.1` is required to be loaded during runtime. If you are running the container under a different user, you may need to first change the permissions of the library (and all the parent directories) to allow the user to access it, then run vLLM with environment variable `VLLM_NCCL_SO_PATH=/root/.config/vllm/nccl/cu12/libnccl.so.2.18.1` .
docs/source/deployment/frameworks/anything-llm.md → docs/deployment/frameworks/anything-llm.md
View file @ a1fe24d9
(deployment-anything-llm)=
# Anything LLM
---
title: Anything LLM
---
[](){ #deployment-anything-llm }
[Anything LLM](https://github.com/Mintplex-Labs/anything-llm) is a full-stack application that enables you to turn any document, resource, or piece of content into context that any LLM can use as references during chatting.
......@@ -25,23 +26,19 @@ vllm serve Qwen/Qwen1.5-32B-Chat-AWQ --max-model-len 4096
- Base URL: http://{vllm server host}:{vllm server port}/v1
- Chat Model Name: `Qwen/Qwen1.5-32B-Chat-AWQ`
:::{image} /assets/deployment/anything-llm-provider.png
:::
![](../../assets/deployment/anything-llm-provider.png)
- Back to home page, New Workspace --> create `vllm` workspace, and start to chat:
:::{image} /assets/deployment/anything-llm-chat-without-doc.png
:::
![](../../assets/deployment/anything-llm-chat-without-doc.png)
- Click the upload button:
- upload the doc
- select the doc and move to the workspace
- save and embed
:::{image} /assets/deployment/anything-llm-upload-doc.png
:::
![](../../assets/deployment/anything-llm-upload-doc.png)
- Chat again:
:::{image} /assets/deployment/anything-llm-chat-with-doc.png
:::
![](../../assets/deployment/anything-llm-chat-with-doc.png)
docs/source/deployment/frameworks/bentoml.md → docs/deployment/frameworks/bentoml.md
View file @ a1fe24d9
(deployment-bentoml)=
# BentoML
---
title: BentoML
---
[](){ #deployment-bentoml }
[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-compliant image and deploy it on Kubernetes.
......
docs/source/deployment/frameworks/cerebrium.md → docs/deployment/frameworks/cerebrium.md
View file @ a1fe24d9
(deployment-cerebrium)=
---
title: Cerebrium
---
[](){ #deployment-cerebrium }
# Cerebrium
:::{raw} html
<p align="center">
<img src="https://i.ibb.co/hHcScTT/Screenshot-2024-06-13-at-10-14-54.png" alt="vLLM_plus_cerebrium"/>
</p>
:::
vLLM can be run on a cloud based GPU machine with [Cerebrium](https://www.cerebrium.ai/), a serverless AI infrastructure platform that makes it easier for companies to build and deploy AI based applications.
......
docs/source/deployment/frameworks/chatbox.md → docs/deployment/frameworks/chatbox.md
View file @ a1fe24d9
(deployment-chatbox)=
# Chatbox
---
title: Chatbox
---
[](){ #deployment-chatbox }
[Chatbox](https://github.com/chatboxai/chatbox) is a desktop client for LLMs, available on Windows, Mac, Linux.
......@@ -27,10 +28,8 @@ vllm serve qwen/Qwen1.5-0.5B-Chat
- API Path: `/chat/completions`
- Model: `qwen/Qwen1.5-0.5B-Chat`
:::{image} /assets/deployment/chatbox-settings.png
:::
![](../../assets/deployment/chatbox-settings.png)
- Go to `Just chat`, and start to chat:
:::{image} /assets/deployment/chatbox-chat.png
:::
![](../../assets/deployment/chatbox-chat.png)
docs/source/deployment/frameworks/dify.md → docs/deployment/frameworks/dify.md
View file @ a1fe24d9
(deployment-dify)=
# Dify
---
title: Dify
---
[](){ #deployment-dify }
[Dify](https://github.com/langgenius/dify) is an open-source LLM app development platform. Its intuitive interface combines agentic AI workflow, RAG pipeline, agent capabilities, model management, observability features, and more, allowing you to quickly move from prototype to production.
......@@ -42,15 +43,12 @@ docker compose up -d
- **Model Name for API Endpoint**: `Qwen/Qwen1.5-7B-Chat`
- **Completion Mode**: `Completion`
:::{image} /assets/deployment/dify-settings.png
:::
![](../../assets/deployment/dify-settings.png)
- To create a test chatbot, go to `Studio → Chatbot → Create from Blank`, then select Chatbot as the type:
:::{image} /assets/deployment/dify-create-chatbot.png
:::
![](../../assets/deployment/dify-create-chatbot.png)
- Click the chatbot you just created to open the chat interface and start interacting with the model:
:::{image} /assets/deployment/dify-chat.png
:::
![](../../assets/deployment/dify-chat.png)
docs/source/deployment/frameworks/dstack.md → docs/deployment/frameworks/dstack.md
View file @ a1fe24d9
(deployment-dstack)=
---
title: dstack
---
[](){ #deployment-dstack }
# dstack
:::{raw} html
<p align="center">
<img src="https://i.ibb.co/71kx6hW/vllm-dstack.png" alt="vLLM_plus_dstack"/>
</p>
:::
vLLM can be run on a cloud based GPU machine with [dstack](https://dstack.ai/), an open-source framework for running LLMs on any cloud. This tutorial assumes that you have already configured credentials, gateway, and GPU quotas on your cloud environment.
......@@ -97,6 +96,5 @@ completion = client.chat.completions.create(
print(completion.choices[0].message.content)
```
:::{note}
dstack automatically handles authentication on the gateway using dstack's tokens. Meanwhile, if you don't want to configure a gateway, you can provision dstack `Task` instead of `Service`. The `Task` is for development purpose only. If you want to know more about hands-on materials how to serve vLLM using dstack, check out [this repository](https://github.com/dstackai/dstack-examples/tree/main/deployment/vllm)
:::
!!! note
dstack automatically handles authentication on the gateway using dstack's tokens. Meanwhile, if you don't want to configure a gateway, you can provision dstack `Task` instead of `Service`. The `Task` is for development purpose only. If you want to know more about hands-on materials how to serve vLLM using dstack, check out [this repository](https://github.com/dstackai/dstack-examples/tree/main/deployment/vllm)
docs/deployment/frameworks/helm.md 0 → 100644
View file @ a1fe24d9
---
title: Helm
---
[](){ #deployment-helm }
A Helm chart to deploy vLLM for Kubernetes
Helm is a package manager for Kubernetes. It will help you to deploy vLLM on k8s and automate the deployment of vLLM Kubernetes applications. With Helm, you can deploy the same framework architecture with different configurations to multiple namespaces by overriding variable values.
This guide will walk you through the process of deploying vLLM with Helm, including the necessary prerequisites, steps for helm installation and documentation on architecture and values file.
## Prerequisites
Before you begin, ensure that you have the following:
- A running Kubernetes cluster
- NVIDIA Kubernetes Device Plugin (`k8s-device-plugin`): This can be found at [https://github.com/NVIDIA/k8s-device-plugin](https://github.com/NVIDIA/k8s-device-plugin)
- Available GPU resources in your cluster
- S3 with the model which will be deployed
## Installing the chart
To install the chart with the release name `test-vllm`:
```console
helm upgrade --install --create-namespace --namespace=ns-vllm test-vllm . -f values.yaml --set secrets.s3endpoint=$ACCESS_POINT --set secrets.s3bucketname=$BUCKET --set secrets.s3accesskeyid=$ACCESS_KEY --set secrets.s3accesskey=$SECRET_KEY
```
## Uninstalling the Chart
To uninstall the `test-vllm` deployment:
```console
helm uninstall test-vllm --namespace=ns-vllm
```
The command removes all the Kubernetes components associated with the
chart **including persistent volumes** and deletes the release.
## Architecture
![](../../assets/deployment/architecture_helm_deployment.png)
## Values
| Key | Type | Default | Description |
|--------------------------------------------|---------|----------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------|
| autoscaling | object | {"enabled":false,"maxReplicas":100,"minReplicas":1,"targetCPUUtilizationPercentage":80} | Autoscaling configuration |
| autoscaling.enabled | bool | false | Enable autoscaling |
| autoscaling.maxReplicas | int | 100 | Maximum replicas |
| autoscaling.minReplicas | int | 1 | Minimum replicas |
| autoscaling.targetCPUUtilizationPercentage | int | 80 | Target CPU utilization for autoscaling |
| configs | object | {} | Configmap |
| containerPort | int | 8000 | Container port |
| customObjects | list | [] | Custom Objects configuration |
| deploymentStrategy | object | {} | Deployment strategy configuration |
| externalConfigs | list | [] | External configuration |
| extraContainers | list | [] | Additional containers configuration |
| extraInit | object | {"pvcStorage":"1Gi","s3modelpath":"relative_s3_model_path/opt-125m", "awsEc2MetadataDisabled": true} | Additional configuration for the init container |
| extraInit.pvcStorage | string | "50Gi" | Storage size of the s3 |
| extraInit.s3modelpath | string | "relative_s3_model_path/opt-125m" | Path of the model on the s3 which hosts model weights and config files |
| extraInit.awsEc2MetadataDisabled | boolean | true | Disables the use of the Amazon EC2 instance metadata service |
| extraPorts | list | [] | Additional ports configuration |
| gpuModels | list | ["TYPE_GPU_USED"] | Type of gpu used |
| image | object | {"command":["vllm","serve","/data/","--served-model-name","opt-125m","--host","0.0.0.0","--port","8000"],"repository":"vllm/vllm-openai","tag":"latest"} | Image configuration |
| image.command | list | ["vllm","serve","/data/","--served-model-name","opt-125m","--host","0.0.0.0","--port","8000"] | Container launch command |
| image.repository | string | "vllm/vllm-openai" | Image repository |
| image.tag | string | "latest" | Image tag |
| livenessProbe | object | {"failureThreshold":3,"httpGet":{"path":"/health","port":8000},"initialDelaySeconds":15,"periodSeconds":10} | Liveness probe configuration |
| livenessProbe.failureThreshold | int | 3 | Number of times after which if a probe fails in a row, Kubernetes considers that the overall check has failed: the container is not alive |
| livenessProbe.httpGet | object | {"path":"/health","port":8000} | Configuration of the Kubelet http request on the server |
| livenessProbe.httpGet.path | string | "/health" | Path to access on the HTTP server |
| livenessProbe.httpGet.port | int | 8000 | Name or number of the port to access on the container, on which the server is listening |
| livenessProbe.initialDelaySeconds | int | 15 | Number of seconds after the container has started before liveness probe is initiated |
| livenessProbe.periodSeconds | int | 10 | How often (in seconds) to perform the liveness probe |
| maxUnavailablePodDisruptionBudget | string | "" | Disruption Budget Configuration |
| readinessProbe | object | {"failureThreshold":3,"httpGet":{"path":"/health","port":8000},"initialDelaySeconds":5,"periodSeconds":5} | Readiness probe configuration |
| readinessProbe.failureThreshold | int | 3 | Number of times after which if a probe fails in a row, Kubernetes considers that the overall check has failed: the container is not ready |
| readinessProbe.httpGet | object | {"path":"/health","port":8000} | Configuration of the Kubelet http request on the server |
| readinessProbe.httpGet.path | string | "/health" | Path to access on the HTTP server |
| readinessProbe.httpGet.port | int | 8000 | Name or number of the port to access on the container, on which the server is listening |
| readinessProbe.initialDelaySeconds | int | 5 | Number of seconds after the container has started before readiness probe is initiated |
| readinessProbe.periodSeconds | int | 5 | How often (in seconds) to perform the readiness probe |
| replicaCount | int | 1 | Number of replicas |
| resources | object | {"limits":{"cpu":4,"memory":"16Gi","nvidia.com/gpu":1},"requests":{"cpu":4,"memory":"16Gi","nvidia.com/gpu":1}} | Resource configuration |
| resources.limits."nvidia.com/gpu" | int | 1 | Number of gpus used |
| resources.limits.cpu | int | 4 | Number of CPUs |
| resources.limits.memory | string | "16Gi" | CPU memory configuration |
| resources.requests."nvidia.com/gpu" | int | 1 | Number of gpus used |
| resources.requests.cpu | int | 4 | Number of CPUs |
| resources.requests.memory | string | "16Gi" | CPU memory configuration |
| secrets | object | {} | Secrets configuration |
| serviceName | string | Service name | |
| servicePort | int | 80 | Service port |
| labels.environment | string | test | Environment name |
docs/source/deployment/frameworks/litellm.md → docs/deployment/frameworks/litellm.md
View file @ a1fe24d9
(deployment-litellm)=
# LiteLLM
---
title: LiteLLM
---
[](){ #deployment-litellm }
[LiteLLM](https://github.com/BerriAI/litellm) call all LLM APIs using the OpenAI format [Bedrock, Huggingface, VertexAI, TogetherAI, Azure, OpenAI, Groq etc.]
......
docs/source/deployment/frameworks/lobe-chat.md → docs/deployment/frameworks/lobe-chat.md
View file @ a1fe24d9
(deployment-lobe-chat)=
# Lobe Chat
---
title: Lobe Chat
---
[](){ #deployment-lobe-chat }
[Lobe Chat](https://github.com/lobehub/lobe-chat) is an open-source, modern-design ChatGPT/LLMs UI/Framework.
......
docs/source/deployment/frameworks/lws.md → docs/deployment/frameworks/lws.md
View file @ a1fe24d9
(deployment-lws)=
# LWS
---
title: LWS
---
[](){ #deployment-lws }
LeaderWorkerSet (LWS) is a Kubernetes API that aims to address common deployment patterns of AI/ML inference workloads.
A major use case is for multi-host/multi-node distributed inference.
......
docs/source/deployment/frameworks/modal.md → docs/deployment/frameworks/modal.md
View file @ a1fe24d9
(deployment-modal)=
# Modal
---
title: Modal
---
[](){ #deployment-modal }
vLLM can be run on cloud GPUs with [Modal](https://modal.com), a serverless computing platform designed for fast auto-scaling.
......
docs/source/deployment/frameworks/open-webui.md → docs/deployment/frameworks/open-webui.md
View file @ a1fe24d9
(deployment-open-webui)=
# Open WebUI
---
title: Open WebUI
---
[](){ #deployment-open-webui }
1. Install the [Docker](https://docs.docker.com/engine/install/)
......@@ -25,5 +26,4 @@ ghcr.io/open-webui/open-webui:main
On the top of the web page, you can see the model `qwen/Qwen1.5-0.5B-Chat`.
:::{image} /assets/deployment/open_webui.png
:::
![](../../assets/deployment/open_webui.png)
docs/source/deployment/frameworks/retrieval_augmented_generation.md → docs/deployment/frameworks/retrieval_augmented_generation.md
View file @ a1fe24d9
(deployment-retrieval-augmented-generation)=
# Retrieval-Augmented Generation
---
title: Retrieval-Augmented Generation
---
[](){ #deployment-retrieval-augmented-generation }
[Retrieval-augmented generation (RAG)](https://en.wikipedia.org/wiki/Retrieval-augmented_generation) is a technique that enables generative artificial intelligence (Gen AI) models to retrieve and incorporate new information. It modifies interactions with a large language model (LLM) so that the model responds to user queries with reference to a specified set of documents, using this information to supplement information from its pre-existing training data. This allows LLMs to use domain-specific and/or updated information. Use cases include providing chatbot access to internal company data or generating responses based on authoritative sources.
......
docs/source/deployment/frameworks/skypilot.md → docs/deployment/frameworks/skypilot.md
View file @ a1fe24d9
(deployment-skypilot)=
---
title: SkyPilot
---
[](){ #deployment-skypilot }
# SkyPilot
:::{raw} html
<p align="center">
<img src="https://imgur.com/yxtzPEu.png" alt="vLLM"/>
</p>
:::
vLLM can be **run and scaled to multiple service replicas on clouds and Kubernetes** with [SkyPilot](https://github.com/skypilot-org/skypilot), an open-source framework for running LLMs on any cloud. More examples for various open models, such as Llama-3, Mixtral, etc, can be found in [SkyPilot AI gallery](https://skypilot.readthedocs.io/en/latest/gallery/index.html).
......@@ -104,10 +103,8 @@ service:
max_completion_tokens: 1
```
:::{raw} html
<details>
<summary>Click to see the full recipe YAML</summary>
:::
```yaml
service:
......@@ -153,9 +150,7 @@ run: |
2>&1 | tee api_server.log
```
:::{raw} html
</details>
:::
Start the serving the Llama-3 8B model on multiple replicas:
......@@ -169,10 +164,8 @@ Wait until the service is ready:
watch -n10 sky serve status vllm
```
:::{raw} html
<details>
<summary>Example outputs:</summary>
:::
```console
Services
......@@ -185,9 +178,7 @@ vllm 1 1 xx.yy.zz.121 18 mins ago 1x GCP([Spot]{'L4': 1}) R
vllm 2 1 xx.yy.zz.245 18 mins ago 1x GCP([Spot]{'L4': 1}) READY us-east4
```
:::{raw} html
</details>
:::
After the service is READY, you can find a single endpoint for the service and access the service with the endpoint:
......@@ -223,10 +214,8 @@ service:
This will scale the service up to when the QPS exceeds 2 for each replica.
:::{raw} html
<details>
<summary>Click to see the full recipe YAML</summary>
:::
```yaml
service:
......@@ -275,9 +264,7 @@ run: |
2>&1 | tee api_server.log
```
:::{raw} html
</details>
:::
To update the service with the new config:
......@@ -295,10 +282,8 @@ sky serve down vllm
It is also possible to access the Llama-3 service with a separate GUI frontend, so the user requests send to the GUI will be load-balanced across replicas.
:::{raw} html
<details>
<summary>Click to see the full GUI YAML</summary>
:::
```yaml
envs:
......@@ -328,9 +313,7 @@ run: |
--stop-token-ids 128009,128001 | tee ~/gradio.log
```
:::{raw} html
</details>
:::
1. Start the chat web UI:
......
docs/source/deployment/frameworks/streamlit.md → docs/deployment/frameworks/streamlit.md
View file @ a1fe24d9
(deployment-streamlit)=
# Streamlit
---
title: Streamlit
---
[](){ #deployment-streamlit }
[Streamlit](https://github.com/streamlit/streamlit) lets you transform Python scripts into interactive web apps in minutes, instead of weeks. Build dashboards, generate reports, or create chat apps.
......@@ -38,5 +39,4 @@ VLLM_API_BASE="http://vllm-server-host:vllm-server-port/v1" streamlit run stream
streamlit run streamlit_openai_chatbot_webserver.py --logger.level=debug
```
:::{image} /assets/deployment/streamlit-chat.png
:::
![](../../assets/deployment/streamlit-chat.png)
docs/source/deployment/frameworks/triton.md → docs/deployment/frameworks/triton.md
View file @ a1fe24d9
(deployment-triton)=
# NVIDIA Triton
---
title: NVIDIA Triton
---
[](){ #deployment-triton }
The [Triton Inference Server](https://github.com/triton-inference-server) hosts a tutorial demonstrating how to quickly deploy a simple [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) model using vLLM. Please see [Deploying a vLLM model in Triton](https://github.com/triton-inference-server/tutorials/blob/main/Quick_Deploy/vLLM/README.md#deploying-a-vllm-model-in-triton) for more details.
docs/source/deployment/integrations/kserve.md → docs/deployment/integrations/kserve.md
View file @ a1fe24d9
(deployment-kserve)=
# KServe
---
title: KServe
---
[](){ #deployment-kserve }
vLLM can be deployed with [KServe](https://github.com/kserve/kserve) on Kubernetes for highly scalable distributed model serving.
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment