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 7, 06:30 UTC
docs: update CPU Docker images to reference Docker Hub instead of AWS ECR (#34882)
Signed-off-by: Maxime Grenu <69890511+cluster2600@users.noreply.github.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Maxime Grenu committed
Mar 4, 2026 at 19:31 UTC
32224f568a6965267ad6d430973bc42c27ded0b1
2 files changed
+16
-9
docs/getting_started/installation/cpu.arm.inc.md
+5
-5
@@ -136,20 +136,20 @@ Testing has been conducted on AWS Graviton3 instances for compatibility.
136
# --8<-- [end:build-wheel-from-source]
137
# --8<-- [start:pre-built-images]
138
139
-To pull the latest image:
139
+To pull the latest image from Docker Hub:
140
141
```bash
142
-docker pull public.ecr.aws/q9t5s3a7/vllm-arm64-cpu-release-repo:latest
142
+docker pull vllm/vllm-openai-cpu:latest-arm64
143
```
144
145
To pull an image with a specific vLLM version:
146
147
```bash
148
export VLLM_VERSION=$(curl -s https://api.github.com/repos/vllm-project/vllm/releases/latest | jq -r .tag_name | sed 's/^v//')
149
-docker pull public.ecr.aws/q9t5s3a7/vllm-arm64-cpu-release-repo:v${VLLM_VERSION}
149
+docker pull vllm/vllm-openai-cpu:v${VLLM_VERSION}-arm64
150
```
151
152
-All available image tags are here: [https://gallery.ecr.aws/q9t5s3a7/vllm-arm64-cpu-release-repo](https://gallery.ecr.aws/q9t5s3a7/vllm-arm64-cpu-release-repo).
152
+All available image tags are here: [https://hub.docker.com/r/vllm/vllm-openai-cpu/tags](https://hub.docker.com/r/vllm/vllm-openai-cpu/tags).
153
154
You can run these images via:
155
@@ -158,7 +158,7 @@ docker run \
158
-v ~/.cache/huggingface:/root/.cache/huggingface \
159
-p 8000:8000 \
160
--env "HF_TOKEN=<secret>" \
161
- public.ecr.aws/q9t5s3a7/vllm-arm64-cpu-release-repo:<tag> <args...>
161
+ vllm/vllm-openai-cpu:latest-arm64 <args...>
162
```
163
164
You can also access the latest code with Docker images. These are not intended for production use and are meant for CI and testing only. They will expire after several days.
docs/getting_started/installation/cpu.x86.inc.md
+11
-4
@@ -161,13 +161,20 @@ uv pip install dist/*.whl
161
# --8<-- [end:build-wheel-from-source]
162
# --8<-- [start:pre-built-images]
163
164
-You can pull the latest available CPU image here via:
164
+You can pull the latest available CPU image from Docker Hub:
165
166
```bash
167
-docker pull public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:latest
167
+docker pull vllm/vllm-openai-cpu:latest-x86_64
168
```
169
170
-If you want a more specific build you can find all published CPU based images here: [https://gallery.ecr.aws/q9t5s3a7/vllm-cpu-release-repo](https://gallery.ecr.aws/q9t5s3a7/vllm-cpu-release-repo)
170
+To pull an image for a specific vLLM version:
171
+
172
+```bash
173
+export VLLM_VERSION=$(curl -s https://api.github.com/repos/vllm-project/vllm/releases/latest | jq -r .tag_name | sed 's/^v//')
174
+docker pull vllm/vllm-openai-cpu:v${VLLM_VERSION}-x86_64
175
+```
176
+
177
+All available image tags are here: [https://hub.docker.com/r/vllm/vllm-openai-cpu/tags](https://hub.docker.com/r/vllm/vllm-openai-cpu/tags)
178
179
You can run these images via:
180
@@ -176,7 +183,7 @@ docker run \
183
-v ~/.cache/huggingface:/root/.cache/huggingface \
184
-p 8000:8000 \
185
--env "HF_TOKEN=<secret>" \
179
- public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:<tag> <args...>
186
+vllm/vllm-openai-cpu:latest-x86_64 <args...>
187
```
188
189
!!! warning