Skip to content

Add parameters for Qwen2.5-vl-7b-instruct model #47

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

Open
prernanookala-ai wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Add parameters for Qwen2.5-vl-7b-instruct model #47

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9e1a8c3
Add parameters for Qwen2.5-vl-7b-instruct model
prernanookala-ai Jan 29, 2026
8c889dd
Update parameters for Qwen2.5-VL per review
prernanookala-ai Jan 31, 2026
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
32 changes: 31 additions & 1 deletion core/helm-charts/vllm/xeon-values.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -243,6 +243,36 @@ modelConfigs:
tensor_parallel_size: "{{ .Values.tensor_parallel_size }}"
pipeline_parallel_size: "{{ .Values.pipeline_parallel_size }}"

"Qwen/Qwen2.5-VL-7B-Instruct":
Copy link
Copy Markdown
Collaborator

@sgurunat sgurunat Jan 30, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for adding the support for this VL model. For better performance in the xeon include these additional variables and extra command arguments. Also tensor parallel is calculated dynamically based on the system configuration where models are deployed.

configMapValues:
VLLM_CPU_KVCACHE_SPACE: "40"
VLLM_RPC_TIMEOUT: "100000"
VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
VLLM_ENGINE_ITERATION_TIMEOUT_S: "120"
VLLM_CPU_NUM_OF_RESERVED_CPU: "0"
VLLM_CPU_SGL_KERNEL: "1"
HF_HUB_DISABLE_XET: "1"
extraCmdArgs:
[
"--block-size",
"128",
"--dtype",
"bfloat16",
"--distributed_executor_backend",
"mp",
"--enable_chunked_prefill",
"--enforce-eager",
"--max-model-len",
"33024",
"--max-num-batched-tokens",
"2048",
"--max-num-seqs",
"256",
]
tensor_parallel_size: "{{ .Values.tensor_parallel_size }}"
pipeline_parallel_size: "{{ .Values.pipeline_parallel_size }}"

Copy link
Copy Markdown
Author

@prernanookala-ai prernanookala-ai Jan 31, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for the suggestions!
I’ve updated xeon-values.yaml to include the additional configMap values and extra command arguments as suggested.
Please let me know if anything else needs adjustment.

configMapValues:
VLLM_SKIP_WARMUP: true
VLLM_CPU_KVCACHE_SPACE: "40"
VLLM_RPC_TIMEOUT: "100000"
VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
VLLM_ENGINE_ITERATION_TIMEOUT_S: "120"
VLLM_CPU_NUM_OF_RESERVED_CPU: "0"
VLLM_CPU_SGL_KERNEL: "1"
Copy link
Copy Markdown

@zahidulhaque zahidulhaque Mar 24, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@prernanookala-ai, Have you tried running Qwen2.5-vl-7b-instruct with this patch? When I used these settings before, the model either failed to start or the server crashed on a /chat/completions request.

For testing you can use the curl command:

curl -X POST "http:///v1/chat/completions"
-H "Content-Type: application/json"
--data '{
"model": "Qwen/Qwen2.5-VL-7B-Instruct",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "Describe this image in one sentence."
},
{
"type": "image_url",
"image_url": {
"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
}
}
]
}
]
}'

Copy link
Copy Markdown
Contributor

@HarikaDev296 HarikaDev296 Mar 26, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@zahidulhaque - You're right, this path is not working for me either.

Below are the values, I've tested and found to be stable for Qwen2,5VL-7B-Instruct, setting VLLM_CPU_KVCACHE_SPACE to 16 and disabling triton resolved the issue on my end.

"Qwen/Qwen2.5-VL-7B-Instruct":
configMapValues:
VLLM_SKIP_WARMUP: "true"
VLLM_CPU_KVCACHE_SPACE: "16"
VLLM_DISABLE_TRITON: "1"
extraCmdArgs: ["--max-model-len","8192"]
tensor_parallel_size: "1"

Let me know if I can update PR with these values?

Copy link
Copy Markdown

@zahidulhaque zahidulhaque Mar 27, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

sure @HarikaDev296 , If things are working fine with the above configuration, you can go ahead and update the code.

Copy link
Copy Markdown

@zahidulhaque zahidulhaque Mar 27, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

also VLLM_CPU_KVCACHE_SPACE: "16" might be too less for mutimodal models. Try setting it to atleast 40. Also make sure to test with curl command once the server is up.

Copy link
Copy Markdown
Contributor

@HarikaDev296 HarikaDev296 Mar 27, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@zahidulhaque - I test Qwen model with below config, increased VLLM_CPU_KVCACHE_SPACE to 40 and was successfully able to get inference.
"Qwen/Qwen2.5-VL-7B-Instruct":
configMapValues:
VLLM_SKIP_WARMUP: "true"
VLLM_CPU_KVCACHE_SPACE: "40"
VLLM_DISABLE_TRITON: "1"
extraCmdArgs: ["--max-model-len","8192"]
tensor_parallel_size: "1"

HF_HUB_DISABLE_XET: "1"
extraCmdArgs:
[
"--block-size",
"128",
"--dtype",
"bfloat16",
"--distributed_executor_backend",
"mp",
"--enable_chunked_prefill",
"--enforce-eager",
"--max-model-len",
"33024",
"--max-num-batched-tokens",
"2048",
"--max-num-seqs",
"256",
]
tensor_parallel_size: "{{ .Values.tensor_parallel_size }}"
pipeline_parallel_size: "{{ .Values.pipeline_parallel_size }}"

defaultModelConfigs:
configMapValues:
VLLM_CPU_KVCACHE_SPACE: "40"
Expand Down Expand Up @@ -270,4 +300,4 @@ defaultModelConfigs:
"256",
]
tensor_parallel_size: "{{ .Values.tensor_parallel_size }}"
pipeline_parallel_size: "{{ .Values.pipeline_parallel_size }}"
pipeline_parallel_size: "{{ .Values.pipeline_parallel_size }}"