Skip to content

Blog: Add Office Hours #52 recap — Semantic Router and DeepLearning.AI course#256

Open
soyr-redhat wants to merge 1 commit into
vllm-project:mainfrom
soyr-redhat:office-hours-52-semantic-router
Open

Blog: Add Office Hours #52 recap — Semantic Router and DeepLearning.AI course#256
soyr-redhat wants to merge 1 commit into
vllm-project:mainfrom
soyr-redhat:office-hours-52-semantic-router

Conversation

@soyr-redhat

@soyr-redhat soyr-redhat commented Jun 25, 2026

Copy link
Copy Markdown

Summary

  • Recap of vLLM Office Hours {#}52 (June 25, 2026), covering the vLLM Semantic Router deep dive and a lightning talk on the new DeepLearning.AI vLLM course
  • Project updates section covers P/D disaggregation on AMD, Codex/Claude Code integration, Day-0 model support (MiniMax M3, Laguna-M.1, GLM 5.2), GLM 5 performance sprint, RL at 1T scale with prime-rl, and vLLM v0.23 release highlights
  • DeepLearning.AI section covers the free "Fast & Efficient LLM Inference with vLLM" course by Cedric Clyburn
  • Semantic Router section covers the Signal-Decision framework, Rust/Candle implementation, LoRA multi-task classification, routing accuracy fine-tuning, and MMLU-Pro benchmarks

Authors

Sawyer Bowerman (@soyr-redhat)

Based on presentations by Michael Goin, Cedric Clyburn, and Christopher Nuland.


View with Codesmith Autofix with Codesmith
Need help on this PR? Tag /codesmith with what you need. Autofix is disabled.

…epLearning.AI course

Signed-off-by: Sawyer Bowerman <sbowerma@redhat.com>

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

Copy link
Copy Markdown

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.

Reviewed commit: bc9877d986

ℹ️ About Codex in GitHub

Codex has been enabled to automatically 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 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".


### Current status

The project has shipped two major releases: [v0.1 Iris](https://vllm.ai/blog/2026-01-05-vllm-sr-iris) in January 2026 and v0.2 Athena in March 2026. The v0.3 Themis release focuses on production stability at scale. The project is open to contributions at [github.com/vllm-project/semantic-router](https://github.com/vllm-project/semantic-router).

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

P2 Badge Update Semantic Router release status

This recap is dated June 25, 2026, but the repo already has _posts/2026-06-05-v0.3-vllm-sr-themis-release.md announcing vLLM Semantic Router v0.3 Themis as released; saying only two major releases have shipped and then describing Themis separately makes the new post stale on publication. This should list Themis as the third shipped release, or otherwise align with the June 5 release post, so readers are not told the latest release has not shipped.

Useful? React with 👍 / 👎.

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.

1 participant