Skip to content

Conversation

@chrisalexiuk-nvidia
Copy link
Contributor

This PR submits both the content of the blog, as well as two .png assets used within the blog.

Signed-off-by: Chris Alexiuk <calexiuk@nvidia.com>
Signed-off-by: Chris Alexiuk <calexiuk@nvidia.com>
@simon-mo
Copy link
Contributor

https://vllm-project-github-hjqjtvj2h-simon-mos-projects.vercel.app/2025/10/23/now_serving_nvidia_nemotron_with_vllm.html

The image seems not rendering.

@simon-mo
Copy link
Contributor

@codex review

Copy link

@chatgpt-codex-connector chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

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

💡 Codex Review

Here are some automated review suggestions for this pull request.

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Comment on lines 23 to 27
![image](../assets/figures/2025-vllm-nvidia-nemotron/figure1.png)
> Figure 1: Chart showing accuracy of Nemotron Nano 2 9B on various popular benchmarks
- **Optimized Thinking:** The model has a new feature called thinking budget which avoids agent overthinking and optimizes for predictable inference cost. The chart below shows that if left alone, models can overthink, increasing inference cost, and in certain cases also reduce accuracy. Thinking budget addresses this challenge by enabling developers to tune the model to achieve the most optimal accuracy-token generation *sweetspot* for their applications.

![image](../assets/figures/2025-vllm-nvidia-nemotron/figure2.png)

Choose a reason for hiding this comment

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

P1 Badge Fix broken asset URLs in Nemotron blog post

Both image references use ../assets/…. Because posts are rendered at /YYYY/MM/DD/slug.html, those relative paths resolve to /2025/10/assets/... and 404 in production. Other posts use root‑relative URLs (/assets/...) to avoid this. Switch these links to root-relative or {{ '/assets/...'}} so the images render on the published page.

Useful? React with 👍 / 👎.

Signed-off-by: Chris Alexiuk <calexiuk@nvidia.com>
@chrisalexiuk-nvidia
Copy link
Contributor Author

@simon-mo - modify image references to match the other examples

Signed-off-by: Chris Alexiuk <calexiuk@nvidia.com>
Signed-off-by: Chris Alexiuk <calexiuk@nvidia.com>
@simon-mo
Copy link
Contributor

The image resolution is very low, any ways we can swap them?

Copy link
Contributor

@simon-mo simon-mo left a comment

Choose a reason for hiding this comment

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

Content LGTM

@chrisalexiuk-nvidia
Copy link
Contributor Author

Hey!

We'd like to move ahead with publishing, and I will update the images once we get higher res. versions, if that's alright?

@simon-mo simon-mo merged commit 2845fcf into vllm-project:main Oct 23, 2025
2 checks passed
@simon-mo
Copy link
Contributor

Done.

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

Successfully merging this pull request may close these issues.

2 participants