Skip to content

VLM inference and validation in Gonka #1026

Open @fedor-konovalenko opened 2026-04-07 12:47 UTC 3 comments Updated 2026-04-27 12:36 UTC
enhancement

Title

VLM inference and validation in Gonka

Summary

Test the possibility of VLM serving validation, add the necessary tools

Motivation

Gonka already employs validation of token sequences generated by distributed nodes serving large language models (LLMs), which enables the detection of fraudulent behavior and dishonest model hosting. A logical next step is to add visual language models in the set of serving models.

Impact

Expected outcome

  • possibility of the VLM serving in Gonka
  • tools for validation

Proposed approach

  • add necessary tools in MLNode
  • Do image-related tasks on the one machine, save artifacts and validate them on the other machine. Include threshold calibration, using "honest" and "fraud" scenarios with "small" (~2B) and "large" (235B) models
  • PR in gonka repo

Intermediate results

Results for "small" visual models - Qwen2-VL-2B-Int4 - Qwen2-VL-2B-Int8 validation are available here For these models F1-score for fraud-detection task is 100%.

Results for large "models" will be added a bit later.


💬 Comments (3)

@fedor-konovalenko commented 2026-04-09 17:32 UTC

Here are the results for large model - /Qwen/Qwen3-VL-235B-A22B-Instruct

link

@fedor-konovalenko commented 2026-04-27 11:20 UTC

And here are the results with the latest version of Gonka-VLM

notebook results

The fraud detection accuracy is about 99%

@fedor-konovalenko commented 2026-04-27 12:36 UTC

Models Proposal

This is a proposal to add the Qwen/Qwen3-VL-235B-A22B-Instruct-FP8 multimodal model to the Gonka inference network.

Validation thresholds for all the models were computed using the standard procedure described in the inference validation scripts README.

There is respective notebook with the details of experiments and gdrive folder with raw inference-validation data.

For the inference the test split (1000 images) of the Flickr8K dataset was used.

Parameter Qwen/Qwen3-VL-235B-A22B-Instruct-FP8
Notebook qwen3-VL-235B_thresholds-new.ipynb
Validation Data link
Model Len 128000
Top-K Logprobs 5
Validation Thresholds 0,0214 / 0,0224
Fraud Accuracy 99%
Tested Against Qwen3-VL-235B-A22B-Instruct-AWQ
VRAM (example setup) ~320GB (4xA100 or 4xH100 GPUs)

All experiments were conducted using MLNode v0.1.0

Qwen3-VL-235B-Instruct is suggested to be deployed with with the following parameters:

additional_args=[
    '--max-model-len', '128000',
    '--gpu-memory-utilization', '0.95'
]

Script for preparing test set is available here.

An example of the inference

python vlm_inference.py \
  --url http://localhost:8801 \
  --exp-dir /root/inference \
  --prompt "Describe the image." \
  --images-dir /root/flickr8k_images/test/ \
  --top-logprobs 5 \
  --temperature 0.99

An example of the validation

python vlm_validation.py \
  --validation-url http://localhost:8001 \
  --inference-artifact /root/inference/inference_results.jsonl \
  --exp-dir /root/validation \
  --images-dir /root/flickr8k_images/test/

🔄 Auto-synced from Issue #1026 every hour.