A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 06:00 UTC
[doc][mkdocs] fix the duplicate Supported features sections in GPU docs (#19606)
Signed-off-by: reidliu41 <reid201711@gmail.com> Co-authored-by: reidliu41 <reid201711@gmail.com>
Reid committed
Jun 14, 2025 at 00:25 UTC
1015296b7947564d8a7258b6f12371f10c955214
3 files changed
+12
-3
docs/getting_started/installation/gpu/cuda.inc.md
+4
-1
@@ -254,7 +254,10 @@ The latest code can contain bugs and may not be stable. Please use it with cauti
254
255
See [deployment-docker-build-image-from-source][deployment-docker-build-image-from-source] for instructions on building the Docker image.
256
257
-## Supported features
257
+# --8<-- [end:build-image-from-source]
258
+# --8<-- [start:supported-features]
259
260
See [feature-x-hardware][feature-x-hardware] compatibility matrix for feature support information.
261
+
262
+# --8<-- [end:supported-features]
263
# --8<-- [end:extra-information]
docs/getting_started/installation/gpu/rocm.inc.md
+4
-1
@@ -217,7 +217,10 @@ docker run -it \
217
218
Where the `<path/to/model>` is the location where the model is stored, for example, the weights for llama2 or llama3 models.
219
220
-## Supported features
220
+# --8<-- [end:build-image-from-source]
221
+# --8<-- [start:supported-features]
222
223
See [feature-x-hardware][feature-x-hardware] compatibility matrix for feature support information.
224
+
225
+# --8<-- [end:supported-features]
226
# --8<-- [end:extra-information]
docs/getting_started/installation/gpu/xpu.inc.md
+4
-1
@@ -63,7 +63,8 @@ $ docker run -it \
63
vllm-xpu-env
64
```
65
66
-## Supported features
66
+# --8<-- [end:build-image-from-source]
67
+# --8<-- [start:supported-features]
68
69
XPU platform supports **tensor parallel** inference/serving and also supports **pipeline parallel** as a beta feature for online serving. We require Ray as the distributed runtime backend. For example, a reference execution like following:
70
@@ -78,4 +79,6 @@ python -m vllm.entrypoints.openai.api_server \
79
```
80
81
By default, a ray instance will be launched automatically if no existing one is detected in the 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.
82
+
83
+# --8<-- [end:supported-features]
84
# --8<-- [end:extra-information]