Skip to content

Update AMD vLLM supported architectures #1054

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
HaiHui886 merged 1 commit into from
May 8, 2026
Merged

Update AMD vLLM supported architectures #1054

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 9 additions & 4 deletions configs/inference/amd-vllm.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,9 +6,9 @@
"engine_images": [
{
"compute_type": "gpu",
"image": "opencsghq/amd-vllm:rocm7.0.0_vllm_0.19.0",
"driver_version": "7.0",
"engine_version": "0.19.0"
"image": "opencsghq/amd-vllm:rocm7.2.1_vllm_0.20.1",
"driver_version": "7.2.1",
"engine_version": "0.20.1"
}
],
"engine_args": [
Expand Down Expand Up @@ -370,13 +370,18 @@
"Phi4ForCausalLMV",
"SarvamMLAForCausalLM",
"SarvamMoEForCausalLM",
"TeleChat3ForCausalLM"
"TeleChat3ForCausalLM",
"DeepseekV4ForCausalLM",
"Rnj1ForCausalLM",
"HYV3ForCausalLM",
"Ministral3ForCausalLM"
],
"tool_call_parsers": {
"DeepseekR1ForCausalLM": "deepseek_r1",
"DeepseekV3ForCausalLM": "deepseek_v3",
"DeepseekV31ForCausalLM": "deepseek_v31",
"DeepseekV32ForCausalLM": "deepseek_v32",
"DeepseekV4ForCausalLM": "deepseek_v4",
"Ernie4_5ForCausalLM": "ernie45",
"Glm4ForCausalLM": "glm47",
"Glm4MoeForCausalLM": "glm45",
Expand Down
17 changes: 13 additions & 4 deletions configs/inference/vllm.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,9 +6,9 @@
"engine_images": [
{
"compute_type": "gpu",
"image": "opencsghq/vllm:v0.19.0",
"image": "opencsghq/vllm:v0.20.1",
"driver_version": "13.0",
"engine_version": "v0.19.0",
"engine_version": "v0.20.1",
"extra_archs": [
"AXK1ForCausalLM",
"ApertusForCausalLM",
Expand Down Expand Up @@ -180,7 +180,11 @@
"UltravoxModel",
"VoxtralForConditionalGeneration",
"VoxtralRealtimeGeneration",
"WhisperForConditionalGeneration"
"WhisperForConditionalGeneration",
"DeepseekV4ForCausalLM",
"Rnj1ForCausalLM",
"HYV3ForCausalLM",
"Ministral3ForCausalLM"
]
},
{
Expand Down Expand Up @@ -393,13 +397,18 @@
"TeleChat2ForCausalLM",
"TeleFLMForCausalLM",
"XverseForCausalLM",
"Zamba2ForCausalLM"
"Zamba2ForCausalLM",
"DeepseekV4ForCausalLM",
"Rnj1ForCausalLM",
"HYV3ForCausalLM",
"Ministral3ForCausalLM"
],
"tool_call_parsers": {
"DeepseekR1ForCausalLM": "deepseek_r1",
"DeepseekV3ForCausalLM": "deepseek_v3",
"DeepseekV31ForCausalLM": "deepseek_v31",
"DeepseekV32ForCausalLM": "deepseek_v32",
"DeepseekV4ForCausalLM": "deepseek_v4",
"Ernie4_5ForCausalLM": "ernie45",
"Glm4ForCausalLM": "glm47",
"Glm4MoeForCausalLM": "glm45",
Expand Down
2 changes: 1 addition & 1 deletion docker/inference/Dockerfile.vllm
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
FROM vllm/vllm-openai:v0.19.0-cu130
FROM vllm/vllm-openai:v0.20.1
RUN pip config set global.index-url https://mirrors.aliyun.com/pypi/simple
RUN pip install --no-cache-dir csghub-sdk==0.7.3 ray supervisor
RUN sed -i 's|http://archive.ubuntu.com/ubuntu|http://mirrors.aliyun.com/ubuntu|g' /etc/apt/sources.list && \
Expand Down
2 changes: 1 addition & 1 deletion docker/inference/Dockerfile.vllm-amd
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
FROM vllm/vllm-openai-rocm:v0.19.0
FROM vllm/vllm-openai-rocm:v0.20.1
RUN pip config set global.index-url https://mirrors.aliyun.com/pypi/simple
RUN pip install --no-cache-dir csghub-sdk==0.7.3 ray supervisor
RUN sed -i 's|http://archive.ubuntu.com/ubuntu|http://mirrors.aliyun.com/ubuntu|g' /etc/apt/sources.list && \
Expand Down
8 changes: 4 additions & 4 deletions docker/inference/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,15 +12,15 @@ echo "$OPENCSG_ACR_PASSWORD" | docker login $OPENCSG_ACR -u $OPENCSG_ACR_USERNAM
```bash
export BUILDX_NO_DEFAULT_ATTESTATIONS=1

# For vllm: opencsg-registry.cn-beijing.cr.aliyuncs.com/opencsghq/vllm:v0.8.5
export IMAGE_TAG=v0.17.0
# For vllm: opencsg-registry.cn-beijing.cr.aliyuncs.com/opencsghq/vllm:v0.20.1
export IMAGE_TAG=v0.20.1
docker buildx build --platform linux/amd64,linux/arm64 \
-t ${OPENCSG_ACR}/opencsghq/vllm:${IMAGE_TAG} \
-f Dockerfile.vllm \
--push .

# For amd-vllm: opencsg-registry.cn-beijing.cr.aliyuncs.com/opencsghq/amd-vllm:rocm7.0.0_vllm_0.19.0
export IMAGE_TAG=rocm7.0.0_vllm_0.19.0
# For amd-vllm: opencsg-registry.cn-beijing.cr.aliyuncs.com/opencsghq/amd-vllm:rocm7.2.1_vllm_0.20.1
export IMAGE_TAG=rocm7.2.1_vllm_0.20.1
docker buildx build --platform linux/amd64 \
-t ${OPENCSG_ACR}/opencsghq/amd-vllm:${IMAGE_TAG} \
-f Dockerfile.vllm-amd \
Expand Down
Loading