issue: min p not being sent to vllm properly #5030

New Issue

GiteaMirror · 2025-11-11T16:10:17-06:00

GiteaMirror commented

2025-11-11 16:10:17 -06:00

Originally created by @ewof on GitHub (May 4, 2025).

Check Existing Issues

I have searched the existing issues and discussions.
I am using the latest version of Open WebUI.

Installation Method

Git Clone

Open WebUI Version

v0.6.5

Ollama Version (if applicable)

N/A

Operating System

artix

Browser (if applicable)

firefox

Confirmation

I have read and followed all instructions in README.md.
I am using the latest version of both Open WebUI and Ollama.
I have included the browser console logs.
I have included the Docker container logs.
I have listed steps to reproduce the bug in detail.

Expected Behavior

the params set in advanced params show up properly in vllm

Actual Behavior

open-webui

vllm

 SamplingParams(n=1, presence_penalty=0.0, frequency_penalty=0.0, repetitio
n_penalty=1.0, temperature=0.15, top_p=1.0, top_k=-1, min_p=0.0, seed=None, stop=[], stop_token_ids=[], bad_words=[], include_stop_str_in_output=False, ignore_eos=False, max_tokens=31515, min
_tokens=0, logprobs=None, prompt_logprobs=None, skip_special_tokens=True, spaces_between_special_tokens=True, truncate_prompt_tokens=None, guided_decoding=None, extra_args=None)

min_p isn't 0.05

Steps to Reproduce

https://docs.vllm.ai/en/latest/deployment/frameworks/open-webui.html

Logs & Screenshots

,

Additional Information

No response

Originally created by @ewof on GitHub (May 4, 2025). ### Check Existing Issues - [x] I have searched the existing issues and discussions. - [x] I am using the latest version of Open WebUI. ### Installation Method Git Clone ### Open WebUI Version v0.6.5 ### Ollama Version (if applicable) N/A ### Operating System artix ### Browser (if applicable) firefox ### Confirmation - [x] I have read and followed all instructions in `README.md`. - [x] I am using the latest version of **both** Open WebUI and Ollama. - [x] I have included the browser console logs. - [x] I have included the Docker container logs. - [x] I have listed steps to reproduce the bug in detail. ### Expected Behavior the params set in advanced params show up properly in vllm ### Actual Behavior open-webui ![Image](https://github.com/user-attachments/assets/fb38f5da-bd00-473a-8911-2fe7d376441d) vllm ``` SamplingParams(n=1, presence_penalty=0.0, frequency_penalty=0.0, repetitio n_penalty=1.0, temperature=0.15, top_p=1.0, top_k=-1, min_p=0.0, seed=None, stop=[], stop_token_ids=[], bad_words=[], include_stop_str_in_output=False, ignore_eos=False, max_tokens=31515, min _tokens=0, logprobs=None, prompt_logprobs=None, skip_special_tokens=True, spaces_between_special_tokens=True, truncate_prompt_tokens=None, guided_decoding=None, extra_args=None) ``` min_p isn't 0.05 ### Steps to Reproduce https://docs.vllm.ai/en/latest/deployment/frameworks/open-webui.html ### Logs & Screenshots , ### Additional Information _No response_

GiteaMirror added the bug label 2025-11-11 16:10:17 -06:00

GiteaMirror closed this issue

2025-11-11 16:10:17 -06:00

GiteaMirror commented

2025-11-11 16:10:18 -06:00

@Nepherpitou commented on GitHub (May 7, 2025):

Not only min_p, OpenWebUI sends only temperature and top_p to OpenAI compatible backends.

@Nepherpitou commented on GitHub (May 7, 2025): Not only `min_p`, OpenWebUI sends only `temperature` and `top_p` to OpenAI compatible backends.

GiteaMirror commented

2025-11-11 16:10:19 -06:00

@tjbck commented on GitHub (May 23, 2025):

Addressed with 797c7d4e56