[BugFix] add manual prefix mapping of qwen2.5vl

[jiangmengyu18]

What this PR does / why we need it?

Bug Fix: Qwen2.5-VL-7B-w8a8 Prefix Mapping: Added manual prefix mappings for the 'qwen2_5_vl' model to the modelslim_config.py file, addressing a bug related to its quantization configuration.

Does this PR introduce any user-facing change?

How was this patch tested?

export ASCEND_RT_VISIBLE_DEVICES=0
export HCCL_IF_IP=127.0.0.1 # node ip
export GLOO_SOCKET_IFNAME="" # network card name
export TP_SOCKET_IFNAME=""
export HCCL_SOCKET_IFNAME=""
export DISAGGREGATED_PREFILL_RANK_TABLE_PATH=/home/vllm_pd/single_pd/ranktable.json
export OMP_PROC_BIND=false
export OMP_NUM_THREADS=100
export VLLM_USE_V1=1
export VLLM_ASCEND_LLMDD_RPC_PORT=5959
export HCCL_OP_EXPANSION_MODE="AIV"

vllm serve qwen2.5vl-7B-w8a8
--host 0.0.0.0
--port 20012
--data-parallel-size 1
--data-parallel-size-local 1
--api-server-count 1
--data-parallel-address 127.0.0.1
--data-parallel-rpc-port 13356
--tensor-parallel-size 1
--mm-processor-cache-gb 0
--quantization ascend
--quantization ascend
--seed 1024
--served-model-name qwen25vl
--quantization ascend
--max-num-seqs 400
--compilation_config '{"cudagraph_capture_sizes":[1,2,4,8,16,32,48,64], "cudagraph_mode": "FULL_DECODE_ONLY"}'
--max-model-len 30000
--max-num-batched-tokens 40000
--trust-remote-code
--allowed-local-media-path /
--gpu-memory-utilization 0.9
--kv-transfer-config
'{"kv_connector": "MooncakeConnectorV1",
"kv_role": "kv_producer",
"kv_port": "30000",
"engine_id": "0",
"kv_connector_module_path": "vllm_ascend.distributed.mooncake_connector",
"kv_connector_extra_config": {
"prefill": {
"dp_size": 1,
"tp_size": 1
},
"decode": {
"dp_size": 1,
"tp_size": 1
}
}

• vLLM version: v0.18.0
• vLLM main: vllm-project/vllm@ed359c4

[gemini-code-assist]

Summary of Changes

Hello, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request resolves a configuration issue by introducing specific prefix mappings for the Qwen2.5VL model within the vllm_ascend quantization module. This ensures that the model's language components are correctly identified and processed, facilitating proper operation and preventing potential errors during model quantization.

Highlights

• Bug Fix: Qwen2.5VL Prefix Mapping: Added manual prefix mappings for the 'qwen2_5_vl' model to the modelslim_config.py file, addressing a bug related to its quantization configuration.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces a manual prefix mapping for the qwen2.5_vl model to support quantization. While the added mappings for the language model components are correct, the configuration for this vision-language model appears to be incomplete as it is missing a prefix mapping for the visual components, which is present for other similar models. This could lead to incorrect quantization of the vision part of the model. I've added a comment with a suggestion to address this.

[github-actions]

👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:‌‌

• A PR should do only one thing, smaller PRs enable faster reviews.
• Every PR should include unit tests and end-to-end tests ‌to ensure it works and is not broken by other future PRs.
• Write the commit message by fulfilling the PR description to help reviewer and future developers understand.

If CI fails, you can run linting and testing checks locally according Contributing and Testing.