20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[CI/Build] Add markdown linter (#11857)

Browse Source 
Signed-off-by: Rafael Vasquez <rafvasq21@gmail.com>
This commit is contained in:
Rafael Vasquez 2025-01-12 03:17:13 -05:00 committed by GitHub
parent b25cfab9a0
commit 43f3d9e699
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
49 changed files with 585 additions and 560 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
.github/workflows/sphinx-lint.yml → .github/workflows/doc-lint.yml vendored
View File

@ -13,7 +13,7 @@ on:
- "docs/**"
jobs:
sphinx-lint:
doc-lint:
runs-on: ubuntu-latest
strategy:
matrix:
@ -29,4 +29,4 @@ jobs:
python -m pip install --upgrade pip
pip install -r requirements-lint.txt
- name: Linting docs
run: tools/sphinx-lint.sh
run: tools/doc-lint.sh

1
docs/README.md
View File

@ -16,4 +16,5 @@ make html
```bash
python -m http.server -d build/html/
```
Launch your browser and open localhost:8000.

1
docs/source/api/model/index.md
View File

@ -9,4 +9,3 @@ interfaces_base
interfaces
adapters
```

2
docs/source/community/sponsors.md
View File

@ -6,6 +6,7 @@ vLLM is a community project. Our compute resources for development and testing a
<!-- Note: Please keep these consistent with README.md. -->
Cash Donations:
- a16z
- Dropbox
- Sequoia Capital
@ -13,6 +14,7 @@ Cash Donations:
- ZhenFund
Compute Resources:
- AMD
- Anyscale
- AWS

4
docs/source/contributing/model/multimodal.md
View File

@ -200,6 +200,7 @@ def get_mm_max_tokens_per_item(self, seq_len: int) -> Mapping[str, int]:
```{note}
Our [actual code](gh-file:vllm/model_executor/models/llava.py) is more abstracted to support vision encoders other than CLIP.
```
:::
::::
@ -248,6 +249,7 @@ def get_dummy_processor_inputs(
mm_data=mm_data,
)
```
:::
::::
@ -312,6 +314,7 @@ def _get_mm_fields_config(
Our [actual code](gh-file:vllm/model_executor/models/llava.py) additionally supports
pre-computed image embeddings, which can be passed to be model via the `image_embeds` argument.
```
:::
::::
@ -369,6 +372,7 @@ def _get_prompt_replacements(
),
]
```
:::
::::

2
docs/source/contributing/overview.md
View File

@ -37,8 +37,6 @@ pytest tests/
Currently, the repository is not fully checked by `mypy`.
```
# Contribution Guidelines
## Issues
If you encounter a bug or have a feature request, please [search existing issues](https://github.com/vllm-project/vllm/issues?q=is%3Aissue) first to see if it has already been reported. If not, please [file a new issue](https://github.com/vllm-project/vllm/issues/new/choose), providing as much relevant information as possible.

4
docs/source/deployment/docker.md
View File

@ -28,8 +28,8 @@ memory to share data between processes under the hood, particularly for tensor p
You can build and run vLLM from source via the provided <gh-file:Dockerfile>. To build vLLM:
```console
$ # optionally specifies: --build-arg max_jobs=8 --build-arg nvcc_threads=2
$ DOCKER_BUILDKIT=1 docker build . --target vllm-openai --tag vllm/vllm-openai
# optionally specifies: --build-arg max_jobs=8 --build-arg nvcc_threads=2
DOCKER_BUILDKIT=1 docker build . --target vllm-openai --tag vllm/vllm-openai
```
```{note}

10
docs/source/deployment/frameworks/cerebrium.md
View File

@ -13,14 +13,14 @@ vLLM can be run on a cloud based GPU machine with [Cerebrium](https://www.cerebr
To install the Cerebrium client, run:
```console
$ pip install cerebrium
$ cerebrium login
pip install cerebrium
cerebrium login
```
Next, create your Cerebrium project, run:
```console
$ cerebrium init vllm-project
cerebrium init vllm-project
```
Next, to install the required packages, add the following to your cerebrium.toml:
@ -58,10 +58,10 @@ def run(prompts: list[str], temperature: float = 0.8, top_p: float = 0.95):
Then, run the following code to deploy it to the cloud:
```console
$ cerebrium deploy
cerebrium deploy
```
If successful, you should be returned a CURL command that you can call inference against. Just remember to end the url with the function name you are calling (in our case` /run`)
If successful, you should be returned a CURL command that you can call inference against. Just remember to end the url with the function name you are calling (in our case`/run`)
```python
curl -X POST https://api.cortex.cerebrium.ai/v4/p-xxxxxx/vllm/run \

10
docs/source/deployment/frameworks/dstack.md
View File

@ -13,16 +13,16 @@ vLLM can be run on a cloud based GPU machine with [dstack](https://dstack.ai/),
To install dstack client, run:
```console
$ pip install "dstack[all]
$ dstack server
pip install "dstack[all]
dstack server
```
Next, to configure your dstack project, run:
```console
$ mkdir -p vllm-dstack
$ cd vllm-dstack
$ dstack init
mkdir -p vllm-dstack
cd vllm-dstack
dstack init
```
Next, to provision a VM instance with LLM of your choice (`NousResearch/Llama-2-7b-chat-hf` for this example), create the following `serve.dstack.yml` file for the dstack `Service`:

12
docs/source/deployment/frameworks/skypilot.md
View File

@ -334,12 +334,12 @@ run: |
1. Start the chat web UI:
```console
sky launch -c gui ./gui.yaml --env ENDPOINT=$(sky serve status --endpoint vllm)
```
```console
sky launch -c gui ./gui.yaml --env ENDPOINT=$(sky serve status --endpoint vllm)
```
2. Then, we can access the GUI at the returned gradio link:
```console
| INFO | stdout | Running on public URL: https://6141e84201ce0bb4ed.gradio.live
```
```console
| INFO | stdout | Running on public URL: https://6141e84201ce0bb4ed.gradio.live
```

2
docs/source/deployment/integrations/llamastack.md
View File

@ -7,7 +7,7 @@ vLLM is also available via [Llama Stack](https://github.com/meta-llama/llama-sta
To install Llama Stack, run
```console
$ pip install llama-stack -q
pip install llama-stack -q
```
## Inference using OpenAI Compatible API

429
docs/source/deployment/k8s.md
View File

@ -14,234 +14,235 @@ Before you begin, ensure that you have the following:
## Deployment Steps
1. **Create a PVC , Secret and Deployment for vLLM**
1. Create a PVC, Secret and Deployment for vLLM
PVC is used to store the model cache and it is optional, you can use hostPath or other storage options
PVC is used to store the model cache and it is optional, you can use hostPath or other storage options
```yaml
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: mistral-7b
namespace: default
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 50Gi
storageClassName: default
volumeMode: Filesystem
```
Secret is optional and only required for accessing gated models, you can skip this step if you are not using gated models
```yaml
apiVersion: v1
kind: Secret
metadata:
name: hf-token-secret
namespace: default
type: Opaque
stringData:
token: "REPLACE_WITH_TOKEN"
```
Next to create the deployment file for vLLM to run the model server. The following example deploys the `Mistral-7B-Instruct-v0.3` model.
Here are two examples for using NVIDIA GPU and AMD GPU.
- NVIDIA GPU
```yaml
apiVersion: apps/v1
kind: Deployment
metadata:
name: mistral-7b
namespace: default
labels:
app: mistral-7b
spec:
replicas: 1
selector:
matchLabels:
app: mistral-7b
template:
metadata:
labels:
app: mistral-7b
spec:
volumes:
- name: cache-volume
persistentVolumeClaim:
claimName: mistral-7b
# vLLM needs to access the host's shared memory for tensor parallel inference.
- name: shm
emptyDir:
medium: Memory
sizeLimit: "2Gi"
containers:
- name: mistral-7b
image: vllm/vllm-openai:latest
command: ["/bin/sh", "-c"]
args: [
"vllm serve mistralai/Mistral-7B-Instruct-v0.3 --trust-remote-code --enable-chunked-prefill --max_num_batched_tokens 1024"
]
env:
- name: HUGGING_FACE_HUB_TOKEN
valueFrom:
secretKeyRef:
name: hf-token-secret
key: token
ports:
- containerPort: 8000
```yaml
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: mistral-7b
namespace: default
spec:
accessModes:
- ReadWriteOnce
resources:
limits:
cpu: "10"
memory: 20G
nvidia.com/gpu: "1"
requests:
cpu: "2"
memory: 6G
nvidia.com/gpu: "1"
volumeMounts:
- mountPath: /root/.cache/huggingface
name: cache-volume
- name: shm
mountPath: /dev/shm
livenessProbe:
httpGet:
path: /health
port: 8000
initialDelaySeconds: 60
periodSeconds: 10
readinessProbe:
httpGet:
path: /health
port: 8000
initialDelaySeconds: 60
periodSeconds: 5
```
storage: 50Gi
storageClassName: default
volumeMode: Filesystem
```
- AMD GPU
Secret is optional and only required for accessing gated models, you can skip this step if you are not using gated models
You can refer to the `deployment.yaml` below if using AMD ROCm GPU like MI300X.
```yaml
apiVersion: v1
kind: Secret
metadata:
name: hf-token-secret
namespace: default
type: Opaque
stringData:
token: "REPLACE_WITH_TOKEN"
```
```yaml
apiVersion: apps/v1
kind: Deployment
metadata:
name: mistral-7b
namespace: default
labels:
app: mistral-7b
spec:
replicas: 1
selector:
matchLabels:
app: mistral-7b
template:
metadata:
labels:
app: mistral-7b
spec:
volumes:
# PVC
- name: cache-volume
persistentVolumeClaim:
claimName: mistral-7b
# vLLM needs to access the host's shared memory for tensor parallel inference.
- name: shm
emptyDir:
medium: Memory
sizeLimit: "8Gi"
hostNetwork: true
hostIPC: true
containers:
- name: mistral-7b
image: rocm/vllm:rocm6.2_mi300_ubuntu20.04_py3.9_vllm_0.6.4
securityContext:
seccompProfile:
type: Unconfined
runAsGroup: 44
capabilities:
add:
- SYS_PTRACE
command: ["/bin/sh", "-c"]
args: [
"vllm serve mistralai/Mistral-7B-v0.3 --port 8000 --trust-remote-code --enable-chunked-prefill --max_num_batched_tokens 1024"
]
env:
- name: HUGGING_FACE_HUB_TOKEN
valueFrom:
secretKeyRef:
name: hf-token-secret
key: token
Next to create the deployment file for vLLM to run the model server. The following example deploys the `Mistral-7B-Instruct-v0.3` model.
Here are two examples for using NVIDIA GPU and AMD GPU.
NVIDIA GPU:
```yaml
apiVersion: apps/v1
kind: Deployment
metadata:
name: mistral-7b
namespace: default
labels:
app: mistral-7b
spec:
replicas: 1
selector:
matchLabels:
app: mistral-7b
template:
metadata:
labels:
app: mistral-7b
spec:
volumes:
- name: cache-volume
persistentVolumeClaim:
claimName: mistral-7b
# vLLM needs to access the host's shared memory for tensor parallel inference.
- name: shm
emptyDir:
medium: Memory
sizeLimit: "2Gi"
containers:
- name: mistral-7b
image: vllm/vllm-openai:latest
command: ["/bin/sh", "-c"]
args: [
"vllm serve mistralai/Mistral-7B-Instruct-v0.3 --trust-remote-code --enable-chunked-prefill --max_num_batched_tokens 1024"
]
env:
- name: HUGGING_FACE_HUB_TOKEN
valueFrom:
secretKeyRef:
name: hf-token-secret
key: token
ports:
- containerPort: 8000
resources:
limits:
cpu: "10"
memory: 20G
nvidia.com/gpu: "1"
requests:
cpu: "2"
memory: 6G
nvidia.com/gpu: "1"
volumeMounts:
- mountPath: /root/.cache/huggingface
name: cache-volume
- name: shm
mountPath: /dev/shm
livenessProbe:
httpGet:
path: /health
port: 8000
initialDelaySeconds: 60
periodSeconds: 10
readinessProbe:
httpGet:
path: /health
port: 8000
initialDelaySeconds: 60
periodSeconds: 5
```
AMD GPU:
You can refer to the `deployment.yaml` below if using AMD ROCm GPU like MI300X.
```yaml
apiVersion: apps/v1
kind: Deployment
metadata:
name: mistral-7b
namespace: default
labels:
app: mistral-7b
spec:
replicas: 1
selector:
matchLabels:
app: mistral-7b
template:
metadata:
labels:
app: mistral-7b
spec:
volumes:
# PVC
- name: cache-volume
persistentVolumeClaim:
claimName: mistral-7b
# vLLM needs to access the host's shared memory for tensor parallel inference.
- name: shm
emptyDir:
medium: Memory
sizeLimit: "8Gi"
hostNetwork: true
hostIPC: true
containers:
- name: mistral-7b
image: rocm/vllm:rocm6.2_mi300_ubuntu20.04_py3.9_vllm_0.6.4
securityContext:
seccompProfile:
type: Unconfined
runAsGroup: 44
capabilities:
add:
- SYS_PTRACE
command: ["/bin/sh", "-c"]
args: [
"vllm serve mistralai/Mistral-7B-v0.3 --port 8000 --trust-remote-code --enable-chunked-prefill --max_num_batched_tokens 1024"
]
env:
- name: HUGGING_FACE_HUB_TOKEN
valueFrom:
secretKeyRef:
name: hf-token-secret
key: token
ports:
- containerPort: 8000
resources:
limits:
cpu: "10"
memory: 20G
amd.com/gpu: "1"
requests:
cpu: "6"
memory: 6G
amd.com/gpu: "1"
volumeMounts:
- name: cache-volume
mountPath: /root/.cache/huggingface
- name: shm
mountPath: /dev/shm
```
You can get the full example with steps and sample yaml files from <https://github.com/ROCm/k8s-device-plugin/tree/master/example/vllm-serve>.
2. Create a Kubernetes Service for vLLM
Next, create a Kubernetes Service file to expose the `mistral-7b` deployment:
```yaml
apiVersion: v1
kind: Service
metadata:
name: mistral-7b
namespace: default
spec:
ports:
- containerPort: 8000
resources:
limits:
cpu: "10"
memory: 20G
amd.com/gpu: "1"
requests:
cpu: "6"
memory: 6G
amd.com/gpu: "1"
volumeMounts:
- name: cache-volume
mountPath: /root/.cache/huggingface
- name: shm
mountPath: /dev/shm
```
You can get the full example with steps and sample yaml files from <https://github.com/ROCm/k8s-device-plugin/tree/master/example/vllm-serve>.
- name: http-mistral-7b
port: 80
protocol: TCP
targetPort: 8000
# The label selector should match the deployment labels & it is useful for prefix caching feature
selector:
app: mistral-7b
sessionAffinity: None
type: ClusterIP
```
2. **Create a Kubernetes Service for vLLM**
3. Deploy and Test
Next, create a Kubernetes Service file to expose the `mistral-7b` deployment:
Apply the deployment and service configurations using `kubectl apply -f <filename>`:
```yaml
apiVersion: v1
kind: Service
metadata:
name: mistral-7b
namespace: default
spec:
ports:
- name: http-mistral-7b
port: 80
protocol: TCP
targetPort: 8000
# The label selector should match the deployment labels & it is useful for prefix caching feature
selector:
app: mistral-7b
sessionAffinity: None
type: ClusterIP
```
```console
kubectl apply -f deployment.yaml
kubectl apply -f service.yaml
```
3. **Deploy and Test**
To test the deployment, run the following `curl` command:
Apply the deployment and service configurations using `kubectl apply -f <filename>`:
```console
curl http://mistral-7b.default.svc.cluster.local/v1/completions \
-H "Content-Type: application/json" \
-d '{
"model": "mistralai/Mistral-7B-Instruct-v0.3",
"prompt": "San Francisco is a",
"max_tokens": 7,
"temperature": 0
}'
```
```console
kubectl apply -f deployment.yaml
kubectl apply -f service.yaml
```
To test the deployment, run the following `curl` command:
```console
curl http://mistral-7b.default.svc.cluster.local/v1/completions \
-H "Content-Type: application/json" \
-d '{
"model": "mistralai/Mistral-7B-Instruct-v0.3",
"prompt": "San Francisco is a",
"max_tokens": 7,
"temperature": 0
}'
```
If the service is correctly deployed, you should receive a response from the vLLM model.
If the service is correctly deployed, you should receive a response from the vLLM model.
## Conclusion

11
docs/source/design/automatic_prefix_caching.md
View File

@ -6,7 +6,7 @@ The core idea of [PagedAttention](https://blog.vllm.ai/2023/06/20/vllm.html) is
To automatically cache the KV cache, we utilize the following key observation: Each KV block can be uniquely identified by the tokens within the block and the tokens in the prefix before the block.
```
```text
Block 1 Block 2 Block 3
[A gentle breeze stirred] [the leaves as children] [laughed in the distance]
Block 1: |<--- block tokens ---->|
@ -14,19 +14,16 @@ Block 2: |<------- prefix ------>| |<--- block tokens --->|
Block 3: |<------------------ prefix -------------------->| |<--- block tokens ---->|
```
In the example above, the KV cache in the first block can be uniquely identified with the tokens “A gentle breeze stirred”. The third block can be uniquely identified with the tokens in the block “laughed in the distance”, along with the prefix tokens “A gentle breeze stirred the leaves as children”. Therefore, we can build the following one-to-one mapping:
```
```text
hash(prefix tokens + block tokens) <--> KV Block
```
With this mapping, we can add another indirection in vLLM’s KV cache management. Previously, each sequence in vLLM maintained a mapping from their logical KV blocks to physical blocks. To achieve automatic caching of KV blocks, we map the logical KV blocks to their hash value and maintain a global hash table of all the physical blocks. In this way, all the KV blocks sharing the same hash value (e.g., shared prefix blocks across two requests) can be mapped to the same physical block and share the memory space.
This design achieves automatic prefix caching without the need of maintaining a tree structure among the KV blocks. More specifically, all of the blocks are independent of each other and can be allocated and freed by itself, which enables us to manages the KV cache as ordinary caches in operating system.
## Generalized Caching Policy
Keeping all the KV blocks in a hash table enables vLLM to cache KV blocks from earlier requests to save memory and accelerate the computation of future requests. For example, if a new request shares the system prompt with the previous request, the KV cache of the shared prompt can directly be used for the new request without recomputation. However, the total KV cache space is limited and we have to decide which KV blocks to keep or evict when the cache is full.
@ -41,5 +38,5 @@ Note that this eviction policy effectively implements the exact policy as in [Ra
However, the hash-based KV cache management gives us the flexibility to handle more complicated serving scenarios and implement more complicated eviction policies beyond the policy above:
- Multi-LoRA serving. When serving requests for multiple LoRA adapters, we can simply let the hash of each KV block to also include the LoRA ID the request is querying for to enable caching for all adapters. In this way, we can jointly manage the KV blocks for different adapters, which simplifies the system implementation and improves the global cache hit rate and efficiency.
- Multi-modal models. When the user input includes more than just discrete tokens, we can use different hashing methods to handle the caching of inputs of different modalities. For example, perceptual hashing for images to cache similar input images.
* Multi-LoRA serving. When serving requests for multiple LoRA adapters, we can simply let the hash of each KV block to also include the LoRA ID the request is querying for to enable caching for all adapters. In this way, we can jointly manage the KV blocks for different adapters, which simplifies the system implementation and improves the global cache hit rate and efficiency.
* Multi-modal models. When the user input includes more than just discrete tokens, we can use different hashing methods to handle the caching of inputs of different modalities. For example, perceptual hashing for images to cache similar input images.

4
docs/source/features/quantization/auto_awq.md
View File

@ -15,7 +15,7 @@ The main benefits are lower latency and memory usage.
You can quantize your own models by installing AutoAWQ or picking one of the [400+ models on Huggingface](https://huggingface.co/models?sort=trending&search=awq).
```console
$ pip install autoawq
pip install autoawq
```
After installing AutoAWQ, you are ready to quantize a model. Here is an example of how to quantize `mistralai/Mistral-7B-Instruct-v0.2`:
@ -47,7 +47,7 @@ print(f'Model is quantized and saved at "{quant_path}"')
To run an AWQ model with vLLM, you can use [TheBloke/Llama-2-7b-Chat-AWQ](https://huggingface.co/TheBloke/Llama-2-7b-Chat-AWQ) with the following command:
```console
$ python examples/offline_inference/llm_engine_example.py --model TheBloke/Llama-2-7b-Chat-AWQ --quantization awq
python examples/offline_inference/llm_engine_example.py --model TheBloke/Llama-2-7b-Chat-AWQ --quantization awq
```
AWQ models are also supported directly through the LLM entrypoint:

7
docs/source/features/quantization/bnb.md
View File

@ -9,7 +9,7 @@ Compared to other quantization methods, BitsAndBytes eliminates the need for cal
Below are the steps to utilize BitsAndBytes with vLLM.
```console
$ pip install bitsandbytes>=0.45.0
pip install bitsandbytes>=0.45.0
```
vLLM reads the model's config file and supports both in-flight quantization and pre-quantized checkpoint.
@ -17,7 +17,7 @@ vLLM reads the model's config file and supports both in-flight quantization and
You can find bitsandbytes quantized models on <https://huggingface.co/models?other=bitsandbytes>.
And usually, these repositories have a config.json file that includes a quantization_config section.
## Read quantized checkpoint.
## Read quantized checkpoint
```python
from vllm import LLM
@ -37,10 +37,11 @@ model_id = "huggyllama/llama-7b"
llm = LLM(model=model_id, dtype=torch.bfloat16, trust_remote_code=True, \
quantization="bitsandbytes", load_format="bitsandbytes")
```
## OpenAI Compatible Server
Append the following to your 4bit model arguments:
```
```console
--quantization bitsandbytes --load-format bitsandbytes
```

4
docs/source/features/quantization/fp8.md
View File

@ -41,7 +41,7 @@ Currently, we load the model at original precision before quantizing down to 8-b
To produce performant FP8 quantized models with vLLM, you'll need to install the [llm-compressor](https://github.com/vllm-project/llm-compressor/) library:
```console
$ pip install llmcompressor
pip install llmcompressor
```
## Quantization Process
@ -98,7 +98,7 @@ tokenizer.save_pretrained(SAVE_DIR)
Install `vllm` and `lm-evaluation-harness`:
```console
$ pip install vllm lm-eval==0.4.4
pip install vllm lm-eval==0.4.4
```
Load and run the model in `vllm`:

2
docs/source/features/quantization/fp8_e4m3_kvcache.md
View File

@ -17,7 +17,7 @@ unquantized model through a quantizer tool (e.g. AMD quantizer or NVIDIA AMMO).
To install AMMO (AlgorithMic Model Optimization):
```console
$ pip install --no-cache-dir --extra-index-url https://pypi.nvidia.com nvidia-ammo
pip install --no-cache-dir --extra-index-url https://pypi.nvidia.com nvidia-ammo
```
Studies have shown that FP8 E4M3 quantization typically only minimally degrades inference accuracy. The most recent silicon

10
docs/source/features/quantization/gguf.md
View File

@ -13,16 +13,16 @@ Currently, vllm only supports loading single-file GGUF models. If you have a mul
To run a GGUF model with vLLM, you can download and use the local GGUF model from [TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF](https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF) with the following command:
```console
$ wget https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf
$ # We recommend using the tokenizer from base model to avoid long-time and buggy tokenizer conversion.
$ vllm serve ./tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf --tokenizer TinyLlama/TinyLlama-1.1B-Chat-v1.0
wget https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf
# We recommend using the tokenizer from base model to avoid long-time and buggy tokenizer conversion.
vllm serve ./tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf --tokenizer TinyLlama/TinyLlama-1.1B-Chat-v1.0
```
You can also add `--tensor-parallel-size 2` to enable tensor parallelism inference with 2 GPUs:
```console
$ # We recommend using the tokenizer from base model to avoid long-time and buggy tokenizer conversion.
$ vllm serve ./tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf --tokenizer TinyLlama/TinyLlama-1.1B-Chat-v1.0 --tensor-parallel-size 2
# We recommend using the tokenizer from base model to avoid long-time and buggy tokenizer conversion.
vllm serve ./tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf --tokenizer TinyLlama/TinyLlama-1.1B-Chat-v1.0 --tensor-parallel-size 2
```
```{warning}

2
docs/source/features/quantization/int8.md
View File

@ -16,7 +16,7 @@ INT8 computation is supported on NVIDIA GPUs with compute capability > 7.5 (Turi
To use INT8 quantization with vLLM, you'll need to install the [llm-compressor](https://github.com/vllm-project/llm-compressor/) library:
```console
$ pip install llmcompressor
pip install llmcompressor
```
## Quantization Process

6
docs/source/features/spec_decode.md
View File

@ -207,7 +207,6 @@ A few important things to consider when using the EAGLE based draft models:
reported in the reference implementation [here](https://github.com/SafeAILab/EAGLE). This issue is under
investigation and tracked here: [https://github.com/vllm-project/vllm/issues/9565](https://github.com/vllm-project/vllm/issues/9565).
A variety of EAGLE draft models are available on the Hugging Face hub:
| Base Model | EAGLE on Hugging Face | # EAGLE Parameters |
@ -224,7 +223,6 @@ A variety of EAGLE draft models are available on the Hugging Face hub:
| Qwen2-7B-Instruct | yuhuili/EAGLE-Qwen2-7B-Instruct | 0.26B |
| Qwen2-72B-Instruct | yuhuili/EAGLE-Qwen2-72B-Instruct | 1.05B |
## Lossless guarantees of Speculative Decoding
In vLLM, speculative decoding aims to enhance inference efficiency while maintaining accuracy. This section addresses the lossless guarantees of
@ -250,8 +248,6 @@ speculative decoding, breaking down the guarantees into three key areas:
same request across runs. For more details, see the FAQ section
titled *Can the output of a prompt vary across runs in vLLM?* in the [FAQs](#faq).
**Conclusion**
While vLLM strives to ensure losslessness in speculative decoding, variations in generated outputs with and without speculative decoding
can occur due to following factors:
@ -259,8 +255,6 @@ can occur due to following factors:
- **Batch Size and Numerical Stability**: Changes in batch size may cause variations in logprobs and output probabilities, potentially
due to non-deterministic behavior in batched operations or numerical instability.
**Mitigation Strategies**
For mitigation strategies, please refer to the FAQ entry *Can the output of a prompt vary across runs in vLLM?* in the [FAQs](#faq).
## Resources for vLLM contributors

42
docs/source/features/tool_calling.md
View File

@ -55,21 +55,24 @@ print(f"Result: {get_weather(**json.loads(tool_call.arguments))}")
```
Example output:
```
```text
Function called: get_weather
Arguments: {"location": "San Francisco, CA", "unit": "fahrenheit"}
Result: Getting the weather for San Francisco, CA in fahrenheit...
```
This example demonstrates:
- Setting up the server with tool calling enabled
- Defining an actual function to handle tool calls
- Making a request with `tool_choice="auto"`
- Handling the structured response and executing the corresponding function
* Setting up the server with tool calling enabled
* Defining an actual function to handle tool calls
* Making a request with `tool_choice="auto"`
* Handling the structured response and executing the corresponding function
You can also specify a particular function using named function calling by setting `tool_choice={"type": "function", "function": {"name": "get_weather"}}`. Note that this will use the guided decoding backend - so the first time this is used, there will be several seconds of latency (or more) as the FSM is compiled for the first time before it is cached for subsequent requests.
Remember that it's the callers responsibility to:
1. Define appropriate tools in the request
2. Include relevant context in the chat messages
3. Handle the tool calls in your application logic
@ -77,6 +80,7 @@ Remember that it's the callers responsibility to:
For more advanced usage, including parallel tool calls and different model-specific parsers, see the sections below.
## Named Function Calling
vLLM supports named function calling in the chat completion API by default. It does so using Outlines through guided decoding, so this is
enabled by default, and will work with any supported model. You are guaranteed a validly-parsable function call - not a
high-quality one.
@ -87,10 +91,10 @@ For best results, we recommend ensuring that the expected output format / schema
To use a named function, you need to define the functions in the `tools` parameter of the chat completion request, and
specify the `name` of one of the tools in the `tool_choice` parameter of the chat completion request.
## Automatic Function Calling
To enable this feature, you should set the following flags:
* `--enable-auto-tool-choice` -- **mandatory** Auto tool choice. tells vLLM that you want to enable the model to generate its own tool calls when it
deems appropriate.
* `--tool-call-parser` -- select the tool parser to use (listed below). Additional tool parsers
@ -104,28 +108,28 @@ from HuggingFace; and you can find an example of this in a `tokenizer_config.jso
If your favorite tool-calling model is not supported, please feel free to contribute a parser & tool use chat template!
### Hermes Models (`hermes`)
All Nous Research Hermes-series models newer than Hermes 2 Pro should be supported.
* `NousResearch/Hermes-2-Pro-*`
* `NousResearch/Hermes-2-Theta-*`
* `NousResearch/Hermes-3-*`
_Note that the Hermes 2 **Theta** models are known to have degraded tool call quality & capabilities due to the merge
step in their creation_.
Flags: `--tool-call-parser hermes`
### Mistral Models (`mistral`)
Supported models:
* `mistralai/Mistral-7B-Instruct-v0.3` (confirmed)
* Additional mistral function-calling models are compatible as well.
Known issues:
1. Mistral 7B struggles to generate parallel tool calls correctly.
2. Mistral's `tokenizer_config.json` chat template requires tool call IDs that are exactly 9 digits, which is
much shorter than what vLLM generates. Since an exception is thrown when this condition
@ -136,13 +140,12 @@ it works with vLLM's tool call IDs (provided `tool_call_id` fields are truncated
* `examples/tool_chat_template_mistral_parallel.jinja` - this is a "better" version that adds a tool-use system prompt
when tools are provided, that results in much better reliability when working with parallel tool calling.
Recommended flags: `--tool-call-parser mistral --chat-template examples/tool_chat_template_mistral_parallel.jinja`
### Llama Models (`llama3_json`)
Supported models:
* `meta-llama/Meta-Llama-3.1-8B-Instruct`
* `meta-llama/Meta-Llama-3.1-70B-Instruct`
* `meta-llama/Meta-Llama-3.1-405B-Instruct`
@ -152,6 +155,7 @@ The tool calling that is supported is the [JSON based tool calling](https://llam
Other tool calling formats like the built in python tool calling or custom tool calling are not supported.
Known issues:
1. Parallel tool calls are not supported.
2. The model can generate parameters with a wrong format, such as generating
an array serialized as string instead of an array.
@ -164,6 +168,7 @@ Recommended flags: `--tool-call-parser llama3_json --chat-template examples/tool
#### IBM Granite
Supported models:
* `ibm-granite/granite-3.0-8b-instruct`
Recommended flags: `--tool-call-parser granite --chat-template examples/tool_chat_template_granite.jinja`
@ -182,42 +187,45 @@ Recommended flags: `--tool-call-parser granite-20b-fc --chat-template examples/t
`examples/tool_chat_template_granite_20b_fc.jinja`: this is a modified chat template from the original on Huggingface, which is not vLLM compatible. It blends function description elements from the Hermes template and follows the same system prompt as "Response Generation" mode from [the paper](https://arxiv.org/abs/2407.00121). Parallel function calls are supported.
### InternLM Models (`internlm`)
Supported models:
* `internlm/internlm2_5-7b-chat` (confirmed)
* Additional internlm2.5 function-calling models are compatible as well
Known issues:
* Although this implementation also supports InternLM2, the tool call results are not stable when testing with the `internlm/internlm2-chat-7b` model.
Recommended flags: `--tool-call-parser internlm --chat-template examples/tool_chat_template_internlm2_tool.jinja`
### Jamba Models (`jamba`)
AI21's Jamba-1.5 models are supported.
* `ai21labs/AI21-Jamba-1.5-Mini`
* `ai21labs/AI21-Jamba-1.5-Large`
Flags: `--tool-call-parser jamba`
### Models with Pythonic Tool Calls (`pythonic`)
A growing number of models output a python list to represent tool calls instead of using JSON. This has the advantage of inherently supporting parallel tool calls and removing ambiguity around the JSON schema required for tool calls. The `pythonic` tool parser can support such models.
As a concrete example, these models may look up the weather in San Francisco and Seattle by generating:
```python
[get_weather(city='San Francisco', metric='celsius'), get_weather(city='Seattle', metric='celsius')]
```
Limitations:
* The model must not generate both text and tool calls in the same generation. This may not be hard to change for a specific model, but the community currently lacks consensus on which tokens to emit when starting and ending tool calls. (In particular, the Llama 3.2 models emit no such tokens.)
* Llama's smaller models struggle to use tools effectively.
Example supported models:
* `meta-llama/Llama-3.2-1B-Instruct`\* (use with `examples/tool_chat_template_llama3.2_pythonic.jinja`)
* `meta-llama/Llama-3.2-3B-Instruct`\* (use with `examples/tool_chat_template_llama3.2_pythonic.jinja`)
* `Team-ACE/ToolACE-8B` (use with `examples/tool_chat_template_toolace.jinja`)
@ -231,7 +239,6 @@ Llama's smaller models frequently fail to emit tool calls in the correct format.
---
## How to write a tool parser plugin
A tool parser plugin is a Python file containing one or more ToolParser implementations. You can write a ToolParser similar to the `Hermes2ProToolParser` in vllm/entrypoints/openai/tool_parsers/hermes_tool_parser.py.
@ -284,7 +291,8 @@ class ExampleToolParser(ToolParser):
```
Then you can use this plugin in the command line like this.
```
```console
--enable-auto-tool-choice \
--tool-parser-plugin <absolute path of the plugin file>
--tool-call-parser example \

2
docs/source/getting_started/faq.md
View File

@ -30,7 +30,7 @@ changes in batch size, or batch expansion in speculative decoding. These batchin
can lead to slightly different logit/logprob values at each step. Such differences can accumulate, potentially resulting in
different tokens being sampled. Once a different token is sampled, further divergence is likely.
**Mitigation Strategies**
## Mitigation Strategies
- For improved stability and reduced variance, use `float32`. Note that this will require more memory.
- If using `bfloat16`, switching to `float16` can also help.

15
docs/source/getting_started/installation/cpu-apple.md
View File

@ -18,25 +18,23 @@ Currently the CPU implementation for macOS supports FP32 and FP16 datatypes.
After installation of XCode and the Command Line Tools, which include Apple Clang, execute the following commands to build and install vLLM from the source.
```
$ git clone https://github.com/vllm-project/vllm.git
$ cd vllm
$ pip install -r requirements-cpu.txt
$ pip install -e .
```console
git clone https://github.com/vllm-project/vllm.git
cd vllm
pip install -r requirements-cpu.txt
pip install -e .
```
```{note}
On macOS the `VLLM_TARGET_DEVICE` is automatically set to `cpu`, which currently is the only supported device.
```
## Troubleshooting
If the build has error like the following snippet where standard C++ headers cannot be found, try to remove and reinstall your
[Command Line Tools for Xcode](https://developer.apple.com/download/all/).
```
```text
[...] fatal error: 'map' file not found
1 | #include <map>
| ^~~~~
@ -48,4 +46,3 @@ If the build has error like the following snippet where standard C++ headers can
| ^~~~~~~~~
1 error generated.
```

44
docs/source/getting_started/installation/cpu-x86.md
View File

@ -32,13 +32,13 @@ Table of contents:
## Quick start using Dockerfile
```console
$ docker build -f Dockerfile.cpu -t vllm-cpu-env --shm-size=4g .
$ docker run -it \
--rm \
--network=host \
--cpuset-cpus=<cpu-id-list, optional> \
--cpuset-mems=<memory-node, optional> \
vllm-cpu-env
docker build -f Dockerfile.cpu -t vllm-cpu-env --shm-size=4g .
docker run -it \
--rm \
--network=host \
--cpuset-cpus=<cpu-id-list, optional> \
--cpuset-mems=<memory-node, optional> \
vllm-cpu-env
```
(build-cpu-backend-from-source)=
@ -48,23 +48,23 @@ $ docker run -it \
- First, install recommended compiler. We recommend to use `gcc/g++ >= 12.3.0` as the default compiler to avoid potential problems. For example, on Ubuntu 22.4, you can run:
```console
$ sudo apt-get update -y
$ sudo apt-get install -y gcc-12 g++-12 libnuma-dev
$ sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-12 10 --slave /usr/bin/g++ g++ /usr/bin/g++-12
sudo apt-get update -y
sudo apt-get install -y gcc-12 g++-12 libnuma-dev
sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-12 10 --slave /usr/bin/g++ g++ /usr/bin/g++-12
```
- Second, install Python packages for vLLM CPU backend building:
```console
$ pip install --upgrade pip
$ pip install cmake>=3.26 wheel packaging ninja "setuptools-scm>=8" numpy
$ pip install -v -r requirements-cpu.txt --extra-index-url https://download.pytorch.org/whl/cpu
pip install --upgrade pip
pip install cmake>=3.26 wheel packaging ninja "setuptools-scm>=8" numpy
pip install -v -r requirements-cpu.txt --extra-index-url https://download.pytorch.org/whl/cpu
```
- Finally, build and install vLLM CPU backend:
```console
$ VLLM_TARGET_DEVICE=cpu python setup.py install
VLLM_TARGET_DEVICE=cpu python setup.py install
```
```{note}
@ -92,18 +92,18 @@ $ VLLM_TARGET_DEVICE=cpu python setup.py install
- We highly recommend to use TCMalloc for high performance memory allocation and better cache locality. For example, on Ubuntu 22.4, you can run:
```console
$ sudo apt-get install libtcmalloc-minimal4 # install TCMalloc library
$ find / -name *libtcmalloc* # find the dynamic link library path
$ export LD_PRELOAD=/usr/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4:$LD_PRELOAD # prepend the library to LD_PRELOAD
$ python examples/offline_inference/basic.py # run vLLM
sudo apt-get install libtcmalloc-minimal4 # install TCMalloc library
find / -name *libtcmalloc* # find the dynamic link library path
export LD_PRELOAD=/usr/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4:$LD_PRELOAD # prepend the library to LD_PRELOAD
python examples/offline_inference/basic.py # run vLLM
```
- When using the online serving, it is recommended to reserve 1-2 CPU cores for the serving framework to avoid CPU oversubscription. For example, on a platform with 32 physical CPU cores, reserving CPU 30 and 31 for the framework and using CPU 0-29 for OpenMP:
```console
$ export VLLM_CPU_KVCACHE_SPACE=40
$ export VLLM_CPU_OMP_THREADS_BIND=0-29
$ vllm serve facebook/opt-125m
export VLLM_CPU_KVCACHE_SPACE=40
export VLLM_CPU_OMP_THREADS_BIND=0-29
vllm serve facebook/opt-125m
```
- If using vLLM CPU backend on a machine with hyper-threading, it is recommended to bind only one OpenMP thread on each physical CPU core using `VLLM_CPU_OMP_THREADS_BIND`. On a hyper-threading enabled platform with 16 logical CPU cores / 8 physical CPU cores:
@ -148,7 +148,7 @@ $ python examples/offline_inference/basic.py
- Using Tensor Parallel for a latency constraints deployment: following GPU backend design, a Megatron-LM's parallel algorithm will be used to shard the model, based on the number of NUMA nodes (e.g. TP = 2 for a two NUMA node system). With [TP feature on CPU](gh-pr:6125) merged, Tensor Parallel is supported for serving and offline inferencing. In general each NUMA node is treated as one GPU card. Below is the example script to enable Tensor Parallel = 2 for serving:
```console
$ VLLM_CPU_KVCACHE_SPACE=40 VLLM_CPU_OMP_THREADS_BIND="0-31|32-63" vllm serve meta-llama/Llama-2-7b-chat-hf -tp=2 --distributed-executor-backend mp
VLLM_CPU_KVCACHE_SPACE=40 VLLM_CPU_OMP_THREADS_BIND="0-31|32-63" vllm serve meta-llama/Llama-2-7b-chat-hf -tp=2 --distributed-executor-backend mp
```
- Using Data Parallel for maximum throughput: to launch an LLM serving endpoint on each NUMA node along with one additional load balancer to dispatch the requests to those endpoints. Common solutions like [Nginx](#nginxloadbalancer) or HAProxy are recommended. Anyscale Ray project provides the feature on LLM [serving](https://docs.ray.io/en/latest/serve/index.html). Here is the example to setup a scalable LLM serving with [Ray Serve](https://github.com/intel/llm-on-ray/blob/main/docs/setup.md).

96
docs/source/getting_started/installation/gpu-cuda.md
View File

@ -17,9 +17,9 @@ vLLM is a Python library that also contains pre-compiled C++ and CUDA (12.1) bin
You can create a new Python environment using `conda`:
```console
$ # (Recommended) Create a new conda environment.
$ conda create -n myenv python=3.12 -y
$ conda activate myenv
# (Recommended) Create a new conda environment.
conda create -n myenv python=3.12 -y
conda activate myenv
```
```{note}
@ -29,9 +29,9 @@ $ conda activate myenv
Or you can create a new Python environment using [uv](https://docs.astral.sh/uv/), a very fast Python environment manager. Please follow the [documentation](https://docs.astral.sh/uv/#getting-started) to install `uv`. After installing `uv`, you can create a new Python environment using the following command:
```console
$ # (Recommended) Create a new uv environment. Use `--seed` to install `pip` and `setuptools` in the environment.
$ uv venv myenv --python 3.12 --seed
$ source myenv/bin/activate
# (Recommended) Create a new uv environment. Use `--seed` to install `pip` and `setuptools` in the environment.
uv venv myenv --python 3.12 --seed
source myenv/bin/activate
```
In order to be performant, vLLM has to compile many cuda kernels. The compilation unfortunately introduces binary incompatibility with other CUDA versions and PyTorch versions, even for the same PyTorch version with different building configurations.
@ -43,18 +43,18 @@ Therefore, it is recommended to install vLLM with a **fresh new** environment. I
You can install vLLM using either `pip` or `uv pip`:
```console
$ # Install vLLM with CUDA 12.1.
$ pip install vllm # If you are using pip.
$ uv pip install vllm # If you are using uv.
# Install vLLM with CUDA 12.1.
pip install vllm # If you are using pip.
uv pip install vllm # If you are using uv.
```
As of now, vLLM's binaries are compiled with CUDA 12.1 and public PyTorch release versions by default. We also provide vLLM binaries compiled with CUDA 11.8 and public PyTorch release versions:
```console
$ # Install vLLM with CUDA 11.8.
$ export VLLM_VERSION=0.6.1.post1
$ export PYTHON_VERSION=310
$ pip install https://github.com/vllm-project/vllm/releases/download/v${VLLM_VERSION}/vllm-${VLLM_VERSION}+cu118-cp${PYTHON_VERSION}-cp${PYTHON_VERSION}-manylinux1_x86_64.whl --extra-index-url https://download.pytorch.org/whl/cu118
# Install vLLM with CUDA 11.8.
export VLLM_VERSION=0.6.1.post1
export PYTHON_VERSION=310
pip install https://github.com/vllm-project/vllm/releases/download/v${VLLM_VERSION}/vllm-${VLLM_VERSION}+cu118-cp${PYTHON_VERSION}-cp${PYTHON_VERSION}-manylinux1_x86_64.whl --extra-index-url https://download.pytorch.org/whl/cu118
```
(install-the-latest-code)=
@ -66,7 +66,7 @@ LLM inference is a fast-evolving field, and the latest code may contain bug fixe
### Install the latest code using `pip`
```console
$ pip install vllm --pre --extra-index-url https://wheels.vllm.ai/nightly
pip install vllm --pre --extra-index-url https://wheels.vllm.ai/nightly
```
`--pre` is required for `pip` to consider pre-released versions.
@ -74,8 +74,8 @@ $ pip install vllm --pre --extra-index-url https://wheels.vllm.ai/nightly
If you want to access the wheels for previous commits (e.g. to bisect the behavior change, performance regression), due to the limitation of `pip`, you have to specify the full URL of the wheel file by embedding the commit hash in the URL:
```console
$ export VLLM_COMMIT=33f460b17a54acb3b6cc0b03f4a17876cff5eafd # use full commit hash from the main branch
$ pip install https://wheels.vllm.ai/${VLLM_COMMIT}/vllm-1.0.0.dev-cp38-abi3-manylinux1_x86_64.whl
export VLLM_COMMIT=33f460b17a54acb3b6cc0b03f4a17876cff5eafd # use full commit hash from the main branch
pip install https://wheels.vllm.ai/${VLLM_COMMIT}/vllm-1.0.0.dev-cp38-abi3-manylinux1_x86_64.whl
```
Note that the wheels are built with Python 3.8 ABI (see [PEP 425](https://peps.python.org/pep-0425/) for more details about ABI), so **they are compatible with Python 3.8 and later**. The version string in the wheel file name (`1.0.0.dev`) is just a placeholder to have a unified URL for the wheels, the actual versions of wheels are contained in the wheel metadata (the wheels listed in the extra index url have correct versions). Although we don't support Python 3.8 any more (because PyTorch 2.5 dropped support for Python 3.8), the wheels are still built with Python 3.8 ABI to keep the same wheel name as before.
@ -85,14 +85,14 @@ Note that the wheels are built with Python 3.8 ABI (see [PEP 425](https://peps.p
Another way to install the latest code is to use `uv`:
```console
$ uv pip install vllm --extra-index-url https://wheels.vllm.ai/nightly
uv pip install vllm --extra-index-url https://wheels.vllm.ai/nightly
```
If you want to access the wheels for previous commits (e.g. to bisect the behavior change, performance regression), you can specify the commit hash in the URL:
```console
$ export VLLM_COMMIT=72d9c316d3f6ede485146fe5aabd4e61dbc59069 # use full commit hash from the main branch
$ uv pip install vllm --extra-index-url https://wheels.vllm.ai/${VLLM_COMMIT}
export VLLM_COMMIT=72d9c316d3f6ede485146fe5aabd4e61dbc59069 # use full commit hash from the main branch
uv pip install vllm --extra-index-url https://wheels.vllm.ai/${VLLM_COMMIT}
```
The `uv` approach works for vLLM `v0.6.6` and later and offers an easy-to-remember command. A unique feature of `uv` is that packages in `--extra-index-url` have [higher priority than the default index](https://docs.astral.sh/uv/pip/compatibility/#packages-that-exist-on-multiple-indexes). If the latest public release is `v0.6.6.post1`, `uv`'s behavior allows installing a commit before `v0.6.6.post1` by specifying the `--extra-index-url`. In contrast, `pip` combines packages from `--extra-index-url` and the default index, choosing only the latest version, which makes it difficult to install a development version prior to the released version.
@ -102,8 +102,8 @@ The `uv` approach works for vLLM `v0.6.6` and later and offers an easy-to-rememb
Another way to access the latest code is to use the docker images:
```console
$ export VLLM_COMMIT=33f460b17a54acb3b6cc0b03f4a17876cff5eafd # use full commit hash from the main branch
$ docker pull public.ecr.aws/q9t5s3a7/vllm-ci-postmerge-repo:${VLLM_COMMIT}
export VLLM_COMMIT=33f460b17a54acb3b6cc0b03f4a17876cff5eafd # use full commit hash from the main branch
docker pull public.ecr.aws/q9t5s3a7/vllm-ci-postmerge-repo:${VLLM_COMMIT}
```
These docker images are used for CI and testing only, and they are not intended for production use. They will be expired after several days.
@ -121,18 +121,18 @@ The latest code can contain bugs and may not be stable. Please use it with cauti
If you only need to change Python code, you can build and install vLLM without compilation. Using `pip`'s [`--editable` flag](https://pip.pypa.io/en/stable/topics/local-project-installs/#editable-installs), changes you make to the code will be reflected when you run vLLM:
```console
$ git clone https://github.com/vllm-project/vllm.git
$ cd vllm
$ VLLM_USE_PRECOMPILED=1 pip install --editable .
git clone https://github.com/vllm-project/vllm.git
cd vllm
VLLM_USE_PRECOMPILED=1 pip install --editable .
```
This will download the latest nightly wheel from https://wheels.vllm.ai/nightly/vllm-1.0.0.dev-cp38-abi3-manylinux1_x86_64.whl and use the compiled libraries from there in the installation.
This will download the [latest nightly wheel](https://wheels.vllm.ai/nightly/vllm-1.0.0.dev-cp38-abi3-manylinux1_x86_64.whl) and use the compiled libraries from there in the installation.
The `VLLM_PRECOMPILED_WHEEL_LOCATION` environment variable can be used instead of `VLLM_USE_PRECOMPILED` to specify a custom path or URL to the wheel file. For example, to use the [0.6.1.post1 PyPi wheel](https://pypi.org/project/vllm/#files):
```console
$ export VLLM_PRECOMPILED_WHEEL_LOCATION=https://files.pythonhosted.org/packages/4a/4c/ee65ba33467a4c0de350ce29fbae39b9d0e7fcd887cc756fa993654d1228/vllm-0.6.3.post1-cp38-abi3-manylinux1_x86_64.whl
$ pip install --editable .
export VLLM_PRECOMPILED_WHEEL_LOCATION=https://files.pythonhosted.org/packages/4a/4c/ee65ba33467a4c0de350ce29fbae39b9d0e7fcd887cc756fa993654d1228/vllm-0.6.3.post1-cp38-abi3-manylinux1_x86_64.whl
pip install --editable .
```
You can find more information about vLLM's wheels [above](#install-the-latest-code).
@ -147,9 +147,9 @@ It is recommended to use the same commit ID for the source code as the vLLM whee
If you want to modify C++ or CUDA code, you'll need to build vLLM from source. This can take several minutes:
```console
$ git clone https://github.com/vllm-project/vllm.git
$ cd vllm
$ pip install -e .
git clone https://github.com/vllm-project/vllm.git
cd vllm
pip install -e .
```
```{tip}
@ -172,11 +172,11 @@ There are scenarios where the PyTorch dependency cannot be easily installed via
To build vLLM using an existing PyTorch installation:
```console
$ git clone https://github.com/vllm-project/vllm.git
$ cd vllm
$ python use_existing_torch.py
$ pip install -r requirements-build.txt
$ pip install -e . --no-build-isolation
git clone https://github.com/vllm-project/vllm.git
cd vllm
python use_existing_torch.py
pip install -r requirements-build.txt
pip install -e . --no-build-isolation
```
#### Use the local cutlass for compilation
@ -185,9 +185,9 @@ Currently, before starting the build process, vLLM fetches cutlass code from Git
To achieve this, you can set the environment variable VLLM_CUTLASS_SRC_DIR to point to your local cutlass directory.
```console
$ git clone https://github.com/vllm-project/vllm.git
$ cd vllm
$ VLLM_CUTLASS_SRC_DIR=/path/to/cutlass pip install -e .
git clone https://github.com/vllm-project/vllm.git
cd vllm
VLLM_CUTLASS_SRC_DIR=/path/to/cutlass pip install -e .
```
#### Troubleshooting
@ -196,8 +196,8 @@ To avoid your system being overloaded, you can limit the number of compilation j
to be run simultaneously, via the environment variable `MAX_JOBS`. For example:
```console
$ export MAX_JOBS=6
$ pip install -e .
export MAX_JOBS=6
pip install -e .
```
This is especially useful when you are building on less powerful machines. For example, when you use WSL it only [assigns 50% of the total memory by default](https://learn.microsoft.com/en-us/windows/wsl/wsl-config#main-wsl-settings), so using `export MAX_JOBS=1` can avoid compiling multiple files simultaneously and running out of memory.
@ -206,22 +206,22 @@ A side effect is a much slower build process.
Additionally, if you have trouble building vLLM, we recommend using the NVIDIA PyTorch Docker image.
```console
$ # Use `--ipc=host` to make sure the shared memory is large enough.
$ docker run --gpus all -it --rm --ipc=host nvcr.io/nvidia/pytorch:23.10-py3
# Use `--ipc=host` to make sure the shared memory is large enough.
docker run --gpus all -it --rm --ipc=host nvcr.io/nvidia/pytorch:23.10-py3
```
If you don't want to use docker, it is recommended to have a full installation of CUDA Toolkit. You can download and install it from [the official website](https://developer.nvidia.com/cuda-toolkit-archive). After installation, set the environment variable `CUDA_HOME` to the installation path of CUDA Toolkit, and make sure that the `nvcc` compiler is in your `PATH`, e.g.:
```console
$ export CUDA_HOME=/usr/local/cuda
$ export PATH="${CUDA_HOME}/bin:$PATH"
export CUDA_HOME=/usr/local/cuda
export PATH="${CUDA_HOME}/bin:$PATH"
```
Here is a sanity check to verify that the CUDA Toolkit is correctly installed:
```console
$ nvcc --version # verify that nvcc is in your PATH
$ ${CUDA_HOME}/bin/nvcc --version # verify that nvcc is in your CUDA_HOME
nvcc --version # verify that nvcc is in your PATH
${CUDA_HOME}/bin/nvcc --version # verify that nvcc is in your CUDA_HOME
```
### Unsupported OS build
@ -231,6 +231,6 @@ vLLM can fully run only on Linux but for development purposes, you can still bui
Simply disable the `VLLM_TARGET_DEVICE` environment variable before installing:
```console
$ export VLLM_TARGET_DEVICE=empty
$ pip install -e .
export VLLM_TARGET_DEVICE=empty
pip install -e .
```

116
docs/source/getting_started/installation/gpu-rocm.md
View File

@ -47,13 +47,13 @@ Their values can be passed in when running `docker build` with `--build-arg` opt
To build vllm on ROCm 6.2 for MI200 and MI300 series, you can use the default:
```console
$ DOCKER_BUILDKIT=1 docker build -f Dockerfile.rocm -t vllm-rocm .
DOCKER_BUILDKIT=1 docker build -f Dockerfile.rocm -t vllm-rocm .
```
To build vllm on ROCm 6.2 for Radeon RX7900 series (gfx1100), you should specify `BUILD_FA` as below:
```console
$ DOCKER_BUILDKIT=1 docker build --build-arg BUILD_FA="0" -f Dockerfile.rocm -t vllm-rocm .
DOCKER_BUILDKIT=1 docker build --build-arg BUILD_FA="0" -f Dockerfile.rocm -t vllm-rocm .
```
To run the above docker image `vllm-rocm`, use the below command:
@ -83,81 +83,81 @@ Where the `<path/to/model>` is the location where the model is stored, for examp
- [ROCm](https://rocm.docs.amd.com/en/latest/deploy/linux/index.html)
- [PyTorch](https://pytorch.org/)
For installing PyTorch, you can start from a fresh docker image, e.g, `rocm/pytorch:rocm6.2_ubuntu20.04_py3.9_pytorch_release_2.3.0`, `rocm/pytorch-nightly`.
For installing PyTorch, you can start from a fresh docker image, e.g, `rocm/pytorch:rocm6.2_ubuntu20.04_py3.9_pytorch_release_2.3.0`, `rocm/pytorch-nightly`.
Alternatively, you can install PyTorch using PyTorch wheels. You can check PyTorch installation guide in PyTorch [Getting Started](https://pytorch.org/get-started/locally/)
Alternatively, you can install PyTorch using PyTorch wheels. You can check PyTorch installation guide in PyTorch [Getting Started](https://pytorch.org/get-started/locally/)
1. Install [Triton flash attention for ROCm](https://github.com/ROCm/triton)
Install ROCm's Triton flash attention (the default triton-mlir branch) following the instructions from [ROCm/triton](https://github.com/ROCm/triton/blob/triton-mlir/README.md)
Install ROCm's Triton flash attention (the default triton-mlir branch) following the instructions from [ROCm/triton](https://github.com/ROCm/triton/blob/triton-mlir/README.md)
```console
$ python3 -m pip install ninja cmake wheel pybind11
$ pip uninstall -y triton
$ git clone https://github.com/OpenAI/triton.git
$ cd triton
$ git checkout e192dba
$ cd python
$ pip3 install .
$ cd ../..
```
```console
python3 -m pip install ninja cmake wheel pybind11
pip uninstall -y triton
git clone https://github.com/OpenAI/triton.git
cd triton
git checkout e192dba
cd python
pip3 install .
cd ../..
```
```{note}
- If you see HTTP issue related to downloading packages during building triton, please try again as the HTTP error is intermittent.
```
```{note}
- If you see HTTP issue related to downloading packages during building triton, please try again as the HTTP error is intermittent.
```
2. Optionally, if you choose to use CK flash attention, you can install [flash attention for ROCm](https://github.com/ROCm/flash-attention/tree/ck_tile)
Install ROCm's flash attention (v2.5.9.post1) following the instructions from [ROCm/flash-attention](https://github.com/ROCm/flash-attention/tree/ck_tile#amd-gpurocm-support)
Alternatively, wheels intended for vLLM use can be accessed under the releases.
Install ROCm's flash attention (v2.5.9.post1) following the instructions from [ROCm/flash-attention](https://github.com/ROCm/flash-attention/tree/ck_tile#amd-gpurocm-support)
Alternatively, wheels intended for vLLM use can be accessed under the releases.
For example, for ROCm 6.2, suppose your gfx arch is `gfx90a`. To get your gfx architecture, run `rocminfo |grep gfx`.
For example, for ROCm 6.2, suppose your gfx arch is `gfx90a`. To get your gfx architecture, run `rocminfo |grep gfx`.
```console
$ git clone https://github.com/ROCm/flash-attention.git
$ cd flash-attention
$ git checkout 3cea2fb
$ git submodule update --init
$ GPU_ARCHS="gfx90a" python3 setup.py install
$ cd ..
```
```console
git clone https://github.com/ROCm/flash-attention.git
cd flash-attention
git checkout 3cea2fb
git submodule update --init
GPU_ARCHS="gfx90a" python3 setup.py install
cd ..
```
```{note}
- You might need to downgrade the "ninja" version to 1.10 it is not used when compiling flash-attention-2 (e.g. `pip install ninja==1.10.2.4`)
```
```{note}
- You might need to downgrade the "ninja" version to 1.10 it is not used when compiling flash-attention-2 (e.g. `pip install ninja==1.10.2.4`)
```
3. Build vLLM. For example, vLLM on ROCM 6.2 can be built with the following steps:
```bash
$ pip install --upgrade pip
```bash
$ pip install --upgrade pip
# Install PyTorch
$ pip uninstall torch -y
$ pip install --no-cache-dir --pre torch==2.6.0.dev20241024 --index-url https://download.pytorch.org/whl/nightly/rocm6.2
# Install PyTorch
$ pip uninstall torch -y
$ pip install --no-cache-dir --pre torch==2.6.0.dev20241024 --index-url https://download.pytorch.org/whl/nightly/rocm6.2
# Build & install AMD SMI
$ pip install /opt/rocm/share/amd_smi
# Build & install AMD SMI
$ pip install /opt/rocm/share/amd_smi
# Install dependencies
$ pip install --upgrade numba scipy huggingface-hub[cli]
$ pip install "numpy<2"
$ pip install -r requirements-rocm.txt
# Install dependencies
$ pip install --upgrade numba scipy huggingface-hub[cli]
$ pip install "numpy<2"
$ pip install -r requirements-rocm.txt
# Build vLLM for MI210/MI250/MI300.
$ export PYTORCH_ROCM_ARCH="gfx90a;gfx942"
$ python3 setup.py develop
```
# Build vLLM for MI210/MI250/MI300.
$ export PYTORCH_ROCM_ARCH="gfx90a;gfx942"
$ python3 setup.py develop
```
This may take 5-10 minutes. Currently, `pip install .` does not work for ROCm installation.
This may take 5-10 minutes. Currently, `pip install .` does not work for ROCm installation.
```{tip}
- Triton flash attention is used by default. For benchmarking purposes, it is recommended to run a warm up step before collecting perf numbers.
- Triton flash attention does not currently support sliding window attention. If using half precision, please use CK flash-attention for sliding window support.
- To use CK flash-attention or PyTorch naive attention, please use this flag `export VLLM_USE_TRITON_FLASH_ATTN=0` to turn off triton flash attention.
- The ROCm version of PyTorch, ideally, should match the ROCm driver version.
```
```{tip}
- Triton flash attention is used by default. For benchmarking purposes, it is recommended to run a warm up step before collecting perf numbers.
- Triton flash attention does not currently support sliding window attention. If using half precision, please use CK flash-attention for sliding window support.
- To use CK flash-attention or PyTorch naive attention, please use this flag `export VLLM_USE_TRITON_FLASH_ATTN=0` to turn off triton flash attention.
- The ROCm version of PyTorch, ideally, should match the ROCm driver version.
```
```{tip}
- For MI300x (gfx942) users, to achieve optimal performance, please refer to [MI300x tuning guide](https://rocm.docs.amd.com/en/latest/how-to/tuning-guides/mi300x/index.html) for performance optimization and tuning tips on system and workflow level.
For vLLM, please refer to [vLLM performance optimization](https://rocm.docs.amd.com/en/latest/how-to/tuning-guides/mi300x/workload.html#vllm-performance-optimization).
```
```{tip}
- For MI300x (gfx942) users, to achieve optimal performance, please refer to [MI300x tuning guide](https://rocm.docs.amd.com/en/latest/how-to/tuning-guides/mi300x/index.html) for performance optimization and tuning tips on system and workflow level.
For vLLM, please refer to [vLLM performance optimization](https://rocm.docs.amd.com/en/latest/how-to/tuning-guides/mi300x/workload.html#vllm-performance-optimization).
```

64
docs/source/getting_started/installation/hpu-gaudi.md
View File

@ -22,8 +22,8 @@ Guide](https://docs.habana.ai/en/latest/PyTorch/Model_Optimization_PyTorch/Optim
### Quick start using Dockerfile
```console
$ docker build -f Dockerfile.hpu -t vllm-hpu-env .
$ docker run -it --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none --cap-add=sys_nice --net=host --rm vllm-hpu-env
docker build -f Dockerfile.hpu -t vllm-hpu-env .
docker run -it --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none --cap-add=sys_nice --net=host --rm vllm-hpu-env
```
```{tip}
@ -37,10 +37,10 @@ If you're observing the following error: `docker: Error response from daemon: Un
To verify that the Intel Gaudi software was correctly installed, run:
```console
$ hl-smi # verify that hl-smi is in your PATH and each Gaudi accelerator is visible
$ apt list --installed | grep habana # verify that habanalabs-firmware-tools, habanalabs-graph, habanalabs-rdma-core, habanalabs-thunk and habanalabs-container-runtime are installed
$ pip list | grep habana # verify that habana-torch-plugin, habana-torch-dataloader, habana-pyhlml and habana-media-loader are installed
$ pip list | grep neural # verify that neural_compressor is installed
hl-smi # verify that hl-smi is in your PATH and each Gaudi accelerator is visible
apt list --installed | grep habana # verify that habanalabs-firmware-tools, habanalabs-graph, habanalabs-rdma-core, habanalabs-thunk and habanalabs-container-runtime are installed
pip list | grep habana # verify that habana-torch-plugin, habana-torch-dataloader, habana-pyhlml and habana-media-loader are installed
pip list | grep neural # verify that neural_compressor is installed
```
Refer to [Intel Gaudi Software Stack
@ -57,8 +57,8 @@ for more details.
Use the following commands to run a Docker image:
```console
$ docker pull vault.habana.ai/gaudi-docker/1.18.0/ubuntu22.04/habanalabs/pytorch-installer-2.4.0:latest
$ docker run -it --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none --cap-add=sys_nice --net=host --ipc=host vault.habana.ai/gaudi-docker/1.18.0/ubuntu22.04/habanalabs/pytorch-installer-2.4.0:latest
docker pull vault.habana.ai/gaudi-docker/1.18.0/ubuntu22.04/habanalabs/pytorch-installer-2.4.0:latest
docker run -it --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none --cap-add=sys_nice --net=host --ipc=host vault.habana.ai/gaudi-docker/1.18.0/ubuntu22.04/habanalabs/pytorch-installer-2.4.0:latest
```
#### Build and Install vLLM
@ -66,18 +66,18 @@ $ docker run -it --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_
To build and install vLLM from source, run:
```console
$ git clone https://github.com/vllm-project/vllm.git
$ cd vllm
$ python setup.py develop
git clone https://github.com/vllm-project/vllm.git
cd vllm
python setup.py develop
```
Currently, the latest features and performance optimizations are developed in Gaudi's [vLLM-fork](https://github.com/HabanaAI/vllm-fork) and we periodically upstream them to vLLM main repo. To install latest [HabanaAI/vLLM-fork](https://github.com/HabanaAI/vllm-fork), run the following:
```console
$ git clone https://github.com/HabanaAI/vllm-fork.git
$ cd vllm-fork
$ git checkout habana_main
$ python setup.py develop
git clone https://github.com/HabanaAI/vllm-fork.git
cd vllm-fork
git checkout habana_main
python setup.py develop
```
## Supported Features
@ -181,7 +181,7 @@ Bucketing allows us to reduce the number of required graphs significantly, but i
Bucketing ranges are determined with 3 parameters - `min`, `step` and `max`. They can be set separately for prompt and decode phase, and for batch size and sequence length dimension. These parameters can be observed in logs during vLLM startup:
```
```text
INFO 08-01 21:37:59 hpu_model_runner.py:493] Prompt bucket config (min, step, max_warmup) bs:[1, 32, 4], seq:[128, 128, 1024]
INFO 08-01 21:37:59 hpu_model_runner.py:499] Generated 24 prompt buckets: [(1, 128), (1, 256), (1, 384), (1, 512), (1, 640), (1, 768), (1, 896), (1, 1024), (2, 128), (2, 256), (2, 384), (2, 512), (2, 640), (2, 768), (2, 896), (2, 1024), (4, 128), (4, 256), (4, 384), (4, 512), (4, 640), (4, 768), (4, 896), (4, 1024)]
INFO 08-01 21:37:59 hpu_model_runner.py:504] Decode bucket config (min, step, max_warmup) bs:[1, 128, 4], seq:[128, 128, 2048]
@ -192,7 +192,7 @@ INFO 08-01 21:37:59 hpu_model_runner.py:509] Generated 48 decode buckets: [(1, 1
Example (with ramp-up)
```
```text
min = 2, step = 32, max = 64
=> ramp_up = (2, 4, 8, 16)
=> stable = (32, 64)
@ -201,7 +201,7 @@ min = 2, step = 32, max = 64
Example (without ramp-up)
```
```text
min = 128, step = 128, max = 512
=> ramp_up = ()
=> stable = (128, 256, 384, 512)
@ -224,7 +224,7 @@ Bucketing is transparent to a client -- padding in sequence length dimension is
Warmup is an optional, but highly recommended step occurring before vLLM server starts listening. It executes a forward pass for each bucket with dummy data. The goal is to pre-compile all graphs and not incur any graph compilation overheads within bucket boundaries during server runtime. Each warmup step is logged during vLLM startup:
```
```text
INFO 08-01 22:26:47 hpu_model_runner.py:1066] [Warmup][Prompt][1/24] batch_size:4 seq_len:1024 free_mem:79.16 GiB
INFO 08-01 22:26:47 hpu_model_runner.py:1066] [Warmup][Prompt][2/24] batch_size:4 seq_len:896 free_mem:55.43 GiB
INFO 08-01 22:26:48 hpu_model_runner.py:1066] [Warmup][Prompt][3/24] batch_size:4 seq_len:768 free_mem:55.43 GiB
@ -273,7 +273,7 @@ When there's large amount of requests pending, vLLM scheduler will attempt to fi
Each described step is logged by vLLM server, as follows (negative values correspond to memory being released):
```
```text
INFO 08-02 17:37:44 hpu_model_runner.py:493] Prompt bucket config (min, step, max_warmup) bs:[1, 32, 4], seq:[128, 128, 1024]
INFO 08-02 17:37:44 hpu_model_runner.py:499] Generated 24 prompt buckets: [(1, 128), (1, 256), (1, 384), (1, 512), (1, 640), (1, 768), (1, 896), (1, 1024), (2, 128), (2, 256), (2, 384), (2, 512), (2, 640), (2, 768), (2, 896), (2, 1024), (4, 128), (4, 256), (4, 384), (4, 512), (4, 640), (4, 768), (4, 896), (4, 1024)]
INFO 08-02 17:37:44 hpu_model_runner.py:504] Decode bucket config (min, step, max_warmup) bs:[1, 128, 4], seq:[128, 128, 2048]
@ -349,19 +349,19 @@ INFO 08-02 17:38:43 hpu_executor.py:91] init_cache_engine took 37.92 GiB of devi
- Default values:
- Prompt:
: - batch size min (`VLLM_PROMPT_BS_BUCKET_MIN`): `1`
- batch size step (`VLLM_PROMPT_BS_BUCKET_STEP`): `min(max_num_seqs, 32)`
- batch size max (`VLLM_PROMPT_BS_BUCKET_MAX`): `min(max_num_seqs, 64)`
- sequence length min (`VLLM_PROMPT_SEQ_BUCKET_MIN`): `block_size`
- sequence length step (`VLLM_PROMPT_SEQ_BUCKET_STEP`): `block_size`
- sequence length max (`VLLM_PROMPT_SEQ_BUCKET_MAX`): `max_model_len`
- batch size min (`VLLM_PROMPT_BS_BUCKET_MIN`): `1`
- batch size step (`VLLM_PROMPT_BS_BUCKET_STEP`): `min(max_num_seqs, 32)`
- batch size max (`VLLM_PROMPT_BS_BUCKET_MAX`): `min(max_num_seqs, 64)`
- sequence length min (`VLLM_PROMPT_SEQ_BUCKET_MIN`): `block_size`
- sequence length step (`VLLM_PROMPT_SEQ_BUCKET_STEP`): `block_size`
- sequence length max (`VLLM_PROMPT_SEQ_BUCKET_MAX`): `max_model_len`
- Decode:
: - batch size min (`VLLM_DECODE_BS_BUCKET_MIN`): `1`
- batch size step (`VLLM_DECODE_BS_BUCKET_STEP`): `min(max_num_seqs, 32)`
- batch size max (`VLLM_DECODE_BS_BUCKET_MAX`): `max_num_seqs`
- sequence length min (`VLLM_DECODE_BLOCK_BUCKET_MIN`): `block_size`
- sequence length step (`VLLM_DECODE_BLOCK_BUCKET_STEP`): `block_size`
- sequence length max (`VLLM_DECODE_BLOCK_BUCKET_MAX`): `max(128, (max_num_seqs*max_model_len)/block_size)`
- batch size min (`VLLM_DECODE_BS_BUCKET_MIN`): `1`
- batch size step (`VLLM_DECODE_BS_BUCKET_STEP`): `min(max_num_seqs, 32)`
- batch size max (`VLLM_DECODE_BS_BUCKET_MAX`): `max_num_seqs`
- sequence length min (`VLLM_DECODE_BLOCK_BUCKET_MIN`): `block_size`
- sequence length step (`VLLM_DECODE_BLOCK_BUCKET_STEP`): `block_size`
- sequence length max (`VLLM_DECODE_BLOCK_BUCKET_MAX`): `max(128, (max_num_seqs*max_model_len)/block_size)`
Additionally, there are HPU PyTorch Bridge environment variables impacting vLLM execution:

8
docs/source/getting_started/installation/neuron.md
View File

@ -123,10 +123,10 @@ python -m pip install --upgrade neuronx-cc==2.* --pre torch-neuronx==2.1.* torch
Once neuronx-cc and transformers-neuronx packages are installed, we will be able to install vllm as follows:
```console
$ git clone https://github.com/vllm-project/vllm.git
$ cd vllm
$ pip install -U -r requirements-neuron.txt
$ VLLM_TARGET_DEVICE="neuron" pip install .
git clone https://github.com/vllm-project/vllm.git
cd vllm
pip install -U -r requirements-neuron.txt
VLLM_TARGET_DEVICE="neuron" pip install .
```
If neuron packages are detected correctly in the installation process, `vllm-0.3.0+neuron212` will be installed.

14
docs/source/getting_started/installation/openvino.md
View File

@ -27,8 +27,8 @@ vLLM powered by OpenVINO supports all LLM models from [vLLM supported models lis
## Quick start using Dockerfile
```console
$ docker build -f Dockerfile.openvino -t vllm-openvino-env .
$ docker run -it --rm vllm-openvino-env
docker build -f Dockerfile.openvino -t vllm-openvino-env .
docker run -it --rm vllm-openvino-env
```
(install-openvino-backend-from-source)=
@ -38,21 +38,21 @@ $ docker run -it --rm vllm-openvino-env
- First, install Python. For example, on Ubuntu 22.04, you can run:
```console
$ sudo apt-get update -y
$ sudo apt-get install python3
sudo apt-get update -y
sudo apt-get install python3
```
- Second, install prerequisites vLLM OpenVINO backend installation:
```console
$ pip install --upgrade pip
$ pip install -r requirements-build.txt --extra-index-url https://download.pytorch.org/whl/cpu
pip install --upgrade pip
pip install -r requirements-build.txt --extra-index-url https://download.pytorch.org/whl/cpu
```
- Finally, install vLLM with OpenVINO backend:
```console
$ PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu" VLLM_TARGET_DEVICE=openvino python -m pip install -v .
PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu" VLLM_TARGET_DEVICE=openvino python -m pip install -v .
```
- [Optional] To use vLLM OpenVINO backend with a GPU device, ensure your system is properly set up. Follow the instructions provided here: [https://docs.openvino.ai/2024/get-started/configurations/configurations-intel-gpu.html](https://docs.openvino.ai/2024/get-started/configurations/configurations-intel-gpu.html).

6
docs/source/getting_started/installation/tpu.md
View File

@ -156,14 +156,14 @@ For more information about using TPUs with GKE, see
You can use <gh-file:Dockerfile.tpu> to build a Docker image with TPU support.
```console
$ docker build -f Dockerfile.tpu -t vllm-tpu .
docker build -f Dockerfile.tpu -t vllm-tpu .
```
Run the Docker image with the following command:
```console
$ # Make sure to add `--privileged --net host --shm-size=16G`.
$ docker run --privileged --net host --shm-size=16G -it vllm-tpu
# Make sure to add `--privileged --net host --shm-size=16G`.
docker run --privileged --net host --shm-size=16G -it vllm-tpu
```
```{note}

24
docs/source/getting_started/installation/xpu.md
View File

@ -40,15 +40,15 @@ $ docker run -it \
- Second, install Python packages for vLLM XPU backend building:
```console
$ source /opt/intel/oneapi/setvars.sh
$ pip install --upgrade pip
$ pip install -v -r requirements-xpu.txt
source /opt/intel/oneapi/setvars.sh
pip install --upgrade pip
pip install -v -r requirements-xpu.txt
```
- Finally, build and install vLLM XPU backend:
```console
$ VLLM_TARGET_DEVICE=xpu python setup.py install
VLLM_TARGET_DEVICE=xpu python setup.py install
```
```{note}
@ -61,14 +61,14 @@ $ VLLM_TARGET_DEVICE=xpu python setup.py install
XPU platform supports tensor-parallel inference/serving and also supports pipeline parallel as a beta feature for online serving. We requires Ray as the distributed runtime backend. For example, a reference execution likes following:
```console
$ python -m vllm.entrypoints.openai.api_server \
$ --model=facebook/opt-13b \
$ --dtype=bfloat16 \
$ --device=xpu \
$ --max_model_len=1024 \
$ --distributed-executor-backend=ray \
$ --pipeline-parallel-size=2 \
$ -tp=8
python -m vllm.entrypoints.openai.api_server \
--model=facebook/opt-13b \
--dtype=bfloat16 \
--device=xpu \
--max_model_len=1024 \
--distributed-executor-backend=ray \
--pipeline-parallel-size=2 \
-tp=8
```
By default, a ray instance will be launched automatically if no existing one is detected in system, with `num-gpus` equals to `parallel_config.world_size`. We recommend properly starting a ray cluster before execution, referring to the <gh-file:examples/online_serving/run_cluster.sh> helper script.

50
docs/source/getting_started/quickstart.md
View File

@ -19,17 +19,17 @@ If you are using NVIDIA GPUs, you can install vLLM using [pip](https://pypi.org/
It's recommended to use [uv](https://docs.astral.sh/uv/), a very fast Python environment manager, to create and manage Python environments. Please follow the [documentation](https://docs.astral.sh/uv/#getting-started) to install `uv`. After installing `uv`, you can create a new Python environment and install vLLM using the following commands:
```console
$ uv venv myenv --python 3.12 --seed
$ source myenv/bin/activate
$ uv pip install vllm
uv venv myenv --python 3.12 --seed
source myenv/bin/activate
uv pip install vllm
```
You can also use [conda](https://docs.conda.io/projects/conda/en/latest/user-guide/getting-started.html) to create and manage Python environments.
```console
$ conda create -n myenv python=3.12 -y
$ conda activate myenv
$ pip install vllm
conda create -n myenv python=3.12 -y
conda activate myenv
pip install vllm
```
```{note}
@ -94,7 +94,7 @@ By default, it starts the server at `http://localhost:8000`. You can specify the
Run the following command to start the vLLM server with the [Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) model:
```console
$ vllm serve Qwen/Qwen2.5-1.5B-Instruct
vllm serve Qwen/Qwen2.5-1.5B-Instruct
```
```{note}
@ -105,7 +105,7 @@ You can learn about overriding it [here](#chat-template).
This server can be queried in the same format as OpenAI API. For example, to list the models:
```console
$ curl http://localhost:8000/v1/models
curl http://localhost:8000/v1/models
```
You can pass in the argument `--api-key` or environment variable `VLLM_API_KEY` to enable the server to check for API key in the header.
@ -115,14 +115,14 @@ You can pass in the argument `--api-key` or environment variable `VLLM_API_KEY`
Once your server is started, you can query the model with input prompts:
```console
$ curl http://localhost:8000/v1/completions \
$ -H "Content-Type: application/json" \
$ -d '{
$ "model": "Qwen/Qwen2.5-1.5B-Instruct",
$ "prompt": "San Francisco is a",
$ "max_tokens": 7,
$ "temperature": 0
$ }'
curl http://localhost:8000/v1/completions \
-H "Content-Type: application/json" \
-d '{
"model": "Qwen/Qwen2.5-1.5B-Instruct",
"prompt": "San Francisco is a",
"max_tokens": 7,
"temperature": 0
}'
```
Since this server is compatible with OpenAI API, you can use it as a drop-in replacement for any applications using OpenAI API. For example, another way to query the server is via the `openai` Python package:
@ -151,15 +151,15 @@ vLLM is designed to also support the OpenAI Chat Completions API. The chat inter
You can use the [create chat completion](https://platform.openai.com/docs/api-reference/chat/completions/create) endpoint to interact with the model:
```console
$ curl http://localhost:8000/v1/chat/completions \
$ -H "Content-Type: application/json" \
$ -d '{
$ "model": "Qwen/Qwen2.5-1.5B-Instruct",
$ "messages": [
$ {"role": "system", "content": "You are a helpful assistant."},
$ {"role": "user", "content": "Who won the world series in 2020?"}
$ ]
$ }'
curl http://localhost:8000/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "Qwen/Qwen2.5-1.5B-Instruct",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Who won the world series in 2020?"}
]
}'
```
Alternatively, you can use the `openai` Python package:

6
docs/source/getting_started/troubleshooting.md
View File

@ -48,6 +48,7 @@ If vLLM crashes and the error trace captures it somewhere around `self.graph.rep
To identify the particular CUDA operation that causes the error, you can add `--enforce-eager` to the command line, or `enforce_eager=True` to the {class}`~vllm.LLM` class to disable the CUDAGraph optimization and isolate the exact CUDA operation that causes the error.
(troubleshooting-incorrect-hardware-driver)=
## Incorrect hardware/driver
If GPU/CPU communication cannot be established, you can use the following Python script and follow the instructions below to confirm whether the GPU/CPU communication is working correctly.
@ -118,13 +119,13 @@ dist.destroy_process_group()
If you are testing with a single node, adjust `--nproc-per-node` to the number of GPUs you want to use:
```console
$ NCCL_DEBUG=TRACE torchrun --nproc-per-node=<number-of-GPUs> test.py
NCCL_DEBUG=TRACE torchrun --nproc-per-node=<number-of-GPUs> test.py
```
If you are testing with multi-nodes, adjust `--nproc-per-node` and `--nnodes` according to your setup and set `MASTER_ADDR` to the correct IP address of the master node, reachable from all nodes. Then, run:
```console
$ NCCL_DEBUG=TRACE torchrun --nnodes 2 --nproc-per-node=2 --rdzv_backend=c10d --rdzv_endpoint=$MASTER_ADDR test.py
NCCL_DEBUG=TRACE torchrun --nnodes 2 --nproc-per-node=2 --rdzv_backend=c10d --rdzv_endpoint=$MASTER_ADDR test.py
```
If the script runs successfully, you should see the message `sanity check is successful!`.
@ -141,6 +142,7 @@ Adjust `--nproc-per-node`, `--nnodes`, and `--node-rank` according to your setup
```
(troubleshooting-python-multiprocessing)=
## Python multiprocessing
### `RuntimeError` Exception

4
docs/source/index.md
View File

@ -1,4 +1,4 @@
# Welcome to vLLM!
# Welcome to vLLM
```{figure} ./assets/logos/vllm-logo-text-light.png
:align: center
@ -186,7 +186,7 @@ community/meetups
community/sponsors
```
# Indices and tables
## Indices and tables
- {ref}`genindex`
- {ref}`modindex`

12
docs/source/models/extensions/runai_model_streamer.md
View File

@ -9,25 +9,25 @@ vLLM supports loading weights in Safetensors format using the Run:ai Model Strea
You first need to install vLLM RunAI optional dependency:
```console
$ pip3 install vllm[runai]
pip3 install vllm[runai]
```
To run it as an OpenAI-compatible server, add the `--load-format runai_streamer` flag:
```console
$ vllm serve /home/meta-llama/Llama-3.2-3B-Instruct --load-format runai_streamer
vllm serve /home/meta-llama/Llama-3.2-3B-Instruct --load-format runai_streamer
```
To run model from AWS S3 object store run:
```console
$ vllm serve s3://core-llm/Llama-3-8b --load-format runai_streamer
vllm serve s3://core-llm/Llama-3-8b --load-format runai_streamer
```
To run model from a S3 compatible object store run:
```console
$ RUNAI_STREAMER_S3_USE_VIRTUAL_ADDRESSING=0 AWS_EC2_METADATA_DISABLED=true AWS_ENDPOINT_URL=https://storage.googleapis.com vllm serve s3://core-llm/Llama-3-8b --load-format runai_streamer
RUNAI_STREAMER_S3_USE_VIRTUAL_ADDRESSING=0 AWS_EC2_METADATA_DISABLED=true AWS_ENDPOINT_URL=https://storage.googleapis.com vllm serve s3://core-llm/Llama-3-8b --load-format runai_streamer
```
## Tunable parameters
@ -38,14 +38,14 @@ You can tune `concurrency` that controls the level of concurrency and number of
For reading from S3, it will be the number of client instances the host is opening to the S3 server.
```console
$ vllm serve /home/meta-llama/Llama-3.2-3B-Instruct --load-format runai_streamer --model-loader-extra-config '{"concurrency":16}'
vllm serve /home/meta-llama/Llama-3.2-3B-Instruct --load-format runai_streamer --model-loader-extra-config '{"concurrency":16}'
```
You can control the size of the CPU Memory buffer to which tensors are read from the file, and limit this size.
You can read further about CPU buffer memory limiting [here](https://github.com/run-ai/runai-model-streamer/blob/master/docs/src/env-vars.md#runai_streamer_memory_limit).
```console
$ vllm serve /home/meta-llama/Llama-3.2-3B-Instruct --load-format runai_streamer --model-loader-extra-config '{"memory_limit":5368709120}'
vllm serve /home/meta-llama/Llama-3.2-3B-Instruct --load-format runai_streamer --model-loader-extra-config '{"memory_limit":5368709120}'
```
```{note}

13
docs/source/models/supported_models.md
View File

@ -45,7 +45,7 @@ Alternatively, you can [open an issue on GitHub](https://github.com/vllm-project
To use models from [ModelScope](https://www.modelscope.cn) instead of HuggingFace Hub, set an environment variable:
```shell
$ export VLLM_USE_MODELSCOPE=True
export VLLM_USE_MODELSCOPE=True
```
And use with `trust_remote_code=True`.
@ -820,19 +820,22 @@ The following table lists those that are tested in vLLM.
_________________
# Model Support Policy
## Model Support Policy
At vLLM, we are committed to facilitating the integration and support of third-party models within our ecosystem. Our approach is designed to balance the need for robustness and the practical limitations of supporting a wide range of models. Here’s how we manage third-party model support:
1. **Community-Driven Support**: We encourage community contributions for adding new models. When a user requests support for a new model, we welcome pull requests (PRs) from the community. These contributions are evaluated primarily on the sensibility of the output they generate, rather than strict consistency with existing implementations such as those in transformers. **Call for contribution:** PRs coming directly from model vendors are greatly appreciated!
2. **Best-Effort Consistency**: While we aim to maintain a level of consistency between the models implemented in vLLM and other frameworks like transformers, complete alignment is not always feasible. Factors like acceleration techniques and the use of low-precision computations can introduce discrepancies. Our commitment is to ensure that the implemented models are functional and produce sensible results.
```{tip}
When comparing the output of `model.generate` from HuggingFace Transformers with the output of `llm.generate` from vLLM, note that the former reads the model's generation config file (i.e., [generation_config.json](https://github.com/huggingface/transformers/blob/19dabe96362803fb0a9ae7073d03533966598b17/src/transformers/generation/utils.py#L1945)) and applies the default parameters for generation, while the latter only uses the parameters passed to the function. Ensure all sampling parameters are identical when comparing outputs.
```
```{tip}
When comparing the output of `model.generate` from HuggingFace Transformers with the output of `llm.generate` from vLLM, note that the former reads the model's generation config file (i.e., [generation_config.json](https://github.com/huggingface/transformers/blob/19dabe96362803fb0a9ae7073d03533966598b17/src/transformers/generation/utils.py#L1945)) and applies the default parameters for generation, while the latter only uses the parameters passed to the function. Ensure all sampling parameters are identical when comparing outputs.
```
3. **Issue Resolution and Model Updates**: Users are encouraged to report any bugs or issues they encounter with third-party models. Proposed fixes should be submitted via PRs, with a clear explanation of the problem and the rationale behind the proposed solution. If a fix for one model impacts another, we rely on the community to highlight and address these cross-model dependencies. Note: for bugfix PRs, it is good etiquette to inform the original author to seek their feedback.
4. **Monitoring and Updates**: Users interested in specific models should monitor the commit history for those models (e.g., by tracking changes in the main/vllm/model_executor/models directory). This proactive approach helps users stay informed about updates and changes that may affect the models they use.
5. **Selective Focus**: Our resources are primarily directed towards models with significant user interest and impact. Models that are less frequently used may receive less attention, and we rely on the community to play a more active role in their upkeep and improvement.
Through this approach, vLLM fosters a collaborative environment where both the core development team and the broader community contribute to the robustness and diversity of the third-party models supported in our ecosystem.

2
docs/source/performance/optimization.md
View File

@ -8,7 +8,7 @@ Due to the auto-regressive nature of transformer architecture, there are times w
The vLLM can preempt requests to free up KV cache space for other requests. Preempted requests are recomputed when sufficient KV cache space becomes
available again. When this occurs, the following warning is printed:
```
```text
WARNING 05-09 00:49:33 scheduler.py:1057 Sequence group 0 is preempted by PreemptionMode.SWAP mode because there is not enough KV cache space. This can affect the end-to-end performance. Increase gpu_memory_utilization or tensor_parallel_size to provide more KV cache memory. total_cumulative_preemption_cnt=1
```

40
docs/source/serving/distributed_serving.md
View File

@ -35,16 +35,16 @@ output = llm.generate("San Franciso is a")
To run multi-GPU serving, pass in the `--tensor-parallel-size` argument when starting the server. For example, to run API server on 4 GPUs:
```console
$ vllm serve facebook/opt-13b \
$ --tensor-parallel-size 4
vllm serve facebook/opt-13b \
--tensor-parallel-size 4
```
You can also additionally specify `--pipeline-parallel-size` to enable pipeline parallelism. For example, to run API server on 8 GPUs with pipeline parallelism and tensor parallelism:
```console
$ vllm serve gpt2 \
$ --tensor-parallel-size 4 \
$ --pipeline-parallel-size 2
vllm serve gpt2 \
--tensor-parallel-size 4 \
--pipeline-parallel-size 2
```
## Running vLLM on multiple nodes
@ -56,21 +56,21 @@ The first step, is to start containers and organize them into a cluster. We have
Pick a node as the head node, and run the following command:
```console
$ bash run_cluster.sh \
$ vllm/vllm-openai \
$ ip_of_head_node \
$ --head \
$ /path/to/the/huggingface/home/in/this/node
bash run_cluster.sh \
vllm/vllm-openai \
ip_of_head_node \
--head \
/path/to/the/huggingface/home/in/this/node
```
On the rest of the worker nodes, run the following command:
```console
$ bash run_cluster.sh \
$ vllm/vllm-openai \
$ ip_of_head_node \
$ --worker \
$ /path/to/the/huggingface/home/in/this/node
bash run_cluster.sh \
vllm/vllm-openai \
ip_of_head_node \
--worker \
/path/to/the/huggingface/home/in/this/node
```
Then you get a ray cluster of containers. Note that you need to keep the shells running these commands alive to hold the cluster. Any shell disconnect will terminate the cluster. In addition, please note that the argument `ip_of_head_node` should be the IP address of the head node, which is accessible by all the worker nodes. A common misunderstanding is to use the IP address of the worker node, which is not correct.
@ -80,16 +80,16 @@ Then, on any node, use `docker exec -it node /bin/bash` to enter the container,
After that, on any node, you can use vLLM as usual, just as you have all the GPUs on one node. The common practice is to set the tensor parallel size to the number of GPUs in each node, and the pipeline parallel size to the number of nodes. For example, if you have 16 GPUs in 2 nodes (8 GPUs per node), you can set the tensor parallel size to 8 and the pipeline parallel size to 2:
```console
$ vllm serve /path/to/the/model/in/the/container \
$ --tensor-parallel-size 8 \
$ --pipeline-parallel-size 2
vllm serve /path/to/the/model/in/the/container \
--tensor-parallel-size 8 \
--pipeline-parallel-size 2
```
You can also use tensor parallel without pipeline parallel, just set the tensor parallel size to the number of GPUs in the cluster. For example, if you have 16 GPUs in 2 nodes (8 GPUs per node), you can set the tensor parallel size to 16:
```console
$ vllm serve /path/to/the/model/in/the/container \
$ --tensor-parallel-size 16
vllm serve /path/to/the/model/in/the/container \
--tensor-parallel-size 16
```
To make tensor parallel performant, you should make sure the communication between nodes is efficient, e.g. using high-speed network cards like Infiniband. To correctly set up the cluster to use Infiniband, append additional arguments like `--privileged -e NCCL_IB_HCA=mlx5` to the `run_cluster.sh` script. Please contact your system administrator for more information on how to set up the flags. One way to confirm if the Infiniband is working is to run vLLM with `NCCL_DEBUG=TRACE` environment variable set, e.g. `NCCL_DEBUG=TRACE vllm serve ...` and check the logs for the NCCL version and the network used. If you find `[send] via NET/Socket` in the logs, it means NCCL uses raw TCP Socket, which is not efficient for cross-node tensor parallel. If you find `[send] via NET/IB/GDRDMA` in the logs, it means NCCL uses Infiniband with GPU-Direct RDMA, which is efficient.

2
docs/source/serving/integrations/langchain.md
View File

@ -7,7 +7,7 @@ vLLM is also available via [LangChain](https://github.com/langchain-ai/langchain
To install LangChain, run
```console
$ pip install langchain langchain_community -q
pip install langchain langchain_community -q
```
To run inference on a single or multiple GPUs, use `VLLM` class from `langchain`.

2
docs/source/serving/integrations/llamaindex.md
View File

@ -7,7 +7,7 @@ vLLM is also available via [LlamaIndex](https://github.com/run-llama/llama_index
To install LlamaIndex, run
```console
$ pip install llama-index-llms-vllm -q
pip install llama-index-llms-vllm -q
```
To run inference on a single or multiple GPUs, use `Vllm` class from `llamaindex`.

2
docs/source/serving/metrics.md
View File

@ -7,7 +7,7 @@ OpenAI compatible API server.
You can start the server using Python, or using [Docker](#deployment-docker):
```console
$ vllm serve unsloth/Llama-3.2-1B-Instruct
vllm serve unsloth/Llama-3.2-1B-Instruct
```
Then query the endpoint to get the latest metrics from the server:

1
docs/source/serving/multimodal_inputs.md
View File

@ -303,6 +303,7 @@ vllm serve llava-hf/llava-onevision-qwen2-0.5b-ov-hf --task generate --max-model
```
Then, you can use the OpenAI client as follows:
```python
from openai import OpenAI

2
docs/source/serving/offline_inference.md
View File

@ -64,7 +64,7 @@ Dynamic quantization is also supported via the `quantization` option -- see [her
#### Context length and batch size
You can further reduce memory usage by limit the context length of the model (`max_model_len` option)
You can further reduce memory usage by limiting the context length of the model (`max_model_len` option)
and the maximum batch size (`max_num_seqs` option).
```python

15
docs/source/serving/openai_compatible_server.md
View File

@ -5,11 +5,13 @@
vLLM provides an HTTP server that implements OpenAI's [Completions API](https://platform.openai.com/docs/api-reference/completions), [Chat API](https://platform.openai.com/docs/api-reference/chat), and more!
You can start the server via the [`vllm serve`](#vllm-serve) command, or through [Docker](#deployment-docker):
```bash
vllm serve NousResearch/Meta-Llama-3-8B-Instruct --dtype auto --api-key token-abc123
```
To call the server, you can use the [official OpenAI Python client](https://github.com/openai/openai-python), or any other HTTP client.
```python
from openai import OpenAI
client = OpenAI(
@ -50,6 +52,7 @@ In addition, we have the following custom APIs:
- Only applicable to [cross-encoder models](../models/pooling_models.md) (`--task score`).
(chat-template)=
## Chat Template
In order for the language model to support chat protocol, vLLM requires the model to include
@ -71,6 +74,7 @@ vLLM community provides a set of chat templates for popular models. You can find
With the inclusion of multi-modal chat APIs, the OpenAI spec now accepts chat messages in a new format which specifies
both a `type` and a `text` field. An example is provided below:
```python
completion = client.chat.completions.create(
model="NousResearch/Meta-Llama-3-8B-Instruct",
@ -120,7 +124,7 @@ with `--enable-request-id-headers`.
> Note that enablement of the headers can impact performance significantly at high QPS
> rates. We recommend implementing HTTP headers at the router level (e.g. via Istio),
> rather than within the vLLM layer for this reason.
> See https://github.com/vllm-project/vllm/pull/11529 for more details.
> See [this PR](https://github.com/vllm-project/vllm/pull/11529) for more details.
```python
completion = client.chat.completions.create(
@ -147,6 +151,7 @@ print(completion._request_id)
## CLI Reference
(vllm-serve)=
### `vllm serve`
The `vllm serve` command is used to launch the OpenAI-compatible server.
@ -175,7 +180,7 @@ uvicorn-log-level: "info"
To use the above config file:
```bash
$ vllm serve SOME_MODEL --config config.yaml
vllm serve SOME_MODEL --config config.yaml
```
```{note}
@ -186,6 +191,7 @@ The order of priorities is `command line > config file values > defaults`.
## API Reference
(completions-api)=
### Completions API
Our Completions API is compatible with [OpenAI's Completions API](https://platform.openai.com/docs/api-reference/completions);
@ -212,6 +218,7 @@ The following extra parameters are supported:
```
(chat-api)=
### Chat API
Our Chat API is compatible with [OpenAI's Chat Completions API](https://platform.openai.com/docs/api-reference/chat);
@ -243,6 +250,7 @@ The following extra parameters are supported:
```
(embeddings-api)=
### Embeddings API
Our Embeddings API is compatible with [OpenAI's Embeddings API](https://platform.openai.com/docs/api-reference/embeddings);
@ -284,6 +292,7 @@ For chat-like input (i.e. if `messages` is passed), these extra parameters are s
```
(tokenizer-api)=
### Tokenizer API
Our Tokenizer API is a simple wrapper over [HuggingFace-style tokenizers](https://huggingface.co/docs/transformers/en/main_classes/tokenizer).
@ -293,6 +302,7 @@ It consists of two endpoints:
- `/detokenize` corresponds to calling `tokenizer.decode()`.
(pooling-api)=
### Pooling API
Our Pooling API encodes input prompts using a [pooling model](../models/pooling_models.md) and returns the corresponding hidden states.
@ -302,6 +312,7 @@ The input format is the same as [Embeddings API](#embeddings-api), but the outpu
Code example: <gh-file:examples/online_serving/openai_pooling_client.py>
(score-api)=
### Score API
Our Score API applies a cross-encoder model to predict scores for sentence pairs.

10
format.sh
View File

@ -41,7 +41,7 @@ MYPY_VERSION=$(mypy --version | awk '{print $2}')
CODESPELL_VERSION=$(codespell --version)
ISORT_VERSION=$(isort --vn)
CLANGFORMAT_VERSION=$(clang-format --version | awk '{print $3}')
SPHINX_LINT_VERSION=$(sphinx-lint --version | awk '{print $2}')
PYMARKDOWNLNT_VERSION=$(pymarkdownlnt version | awk '{print $1}')
# # params: tool name, tool version, required version
tool_version_check() {
@ -58,7 +58,7 @@ tool_version_check "mypy" "$MYPY_VERSION"
tool_version_check "isort" "$ISORT_VERSION"
tool_version_check "codespell" "$CODESPELL_VERSION"
tool_version_check "clang-format" "$CLANGFORMAT_VERSION"
tool_version_check "sphinx-lint" "$SPHINX_LINT_VERSION"
tool_version_check "pymarkdownlnt" "$PYMARKDOWNLNT_VERSION"
YAPF_FLAGS=(
'--recursive'
@ -316,6 +316,6 @@ else
echo "✨🎉 Format check passed! Congratulations! 🎉✨"
fi
echo 'vLLM sphinx-lint:'
tools/sphinx-lint.sh
echo 'vLLM sphinx-lint: Done'
echo 'vLLM doc-lint:'
tools/doc-lint.sh
echo 'vLLM doc-lint: Done'

6
pyproject.toml
View File

@ -101,3 +101,9 @@ markers = [
"skip_v1: do not run this test with v1",
"optional: optional tests that are automatically skipped, include --optional to run them",
]
[tool.pymarkdown]
plugins.md013.enabled = false # line-length
plugins.md041.enabled = false # first-line-h1
plugins.md033.enabled = false # inline-html
plugins.md024.allow_different_nesting = true # no-duplicate-headers

2
requirements-lint.txt
View File

@ -6,7 +6,7 @@ ruff==0.6.5
codespell==2.3.0
isort==5.13.2
clang-format==18.1.5
sphinx-lint==1.0.0
pymarkdownlnt==0.9.26
# type checking
mypy==1.11.1

3
tools/doc-lint.sh Executable file
View File

@ -0,0 +1,3 @@
#!/bin/bash
pymarkdownlnt scan docs -r

3
tools/sphinx-lint.sh
View File

@ -1,3 +0,0 @@
#!/bin/bash
sphinx-lint --disable trailing-whitespace,missing-final-newline docs