Skip to content
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.

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

[Bug] min_p from request is not used #2682

Open
2 of 3 tasks
ErykCh opened this issue Oct 29, 2024 · 1 comment
Open
2 of 3 tasks

[Bug] min_p from request is not used #2682

ErykCh opened this issue Oct 29, 2024 · 1 comment
Assignees

Comments

@ErykCh
Copy link

ErykCh commented Oct 29, 2024

Checklist

  • 1. I have searched related issues but cannot get the expected help.
  • 2. The bug has not been fixed in the latest version.
  • 3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback.

Describe the bug

Information about min_p in request is not used during inference:

image

Reproduction

Create a request with min_p and check logs if parameter was used:

response = requests.post(
    "http://localhost:8000/v1/chat/completions",
    headers={
        "Content-Type": "application/json",
    },
    json={
        "model": "Qwen_2.5",
        "messages": [
            {"role": "system", "content": ""},
            {"role": "user", "content": "Hi"}
        ],
        "presence_penalty": 0.0,
        "frequency_penalty": 0.0,
        "repetition_penalty": 1.05,
        "temperature": 0.1,
        "top_k": 2,
        "top_p": 0.9,
        "min_p": 0.3,
        "max_tokens": 10480,
        "seed": 1234
    }
)

Environment

docker run --runtime nvidia --gpus all --shm-size 64g -d --name lmdeploy-QWEN_2.5_32B --restart unless-stopped -v ~/.cache/huggingface:/root/.cache/huggingface -p 8000:8000 openmmlab/lmdeploy:latest-cu12 lmdeploy serve api_server --server-port 8000 --model-name Qwen_2.5 --backend turbomind --model-format awq --enable-prefix-caching --log-level DEBUG Qwen/Qwen2.5-32B-Instruct-AWQ

Error traceback

No response

@AllentDan
Copy link
Collaborator

May try #2681

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants