docs: add NVIDIA Dynamo integration proposal #373
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
✅ Deploy Preview for vllm-semantic-router ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
👥 vLLM Semantic Team NotificationThe following members have been identified for the changed files in this PR and have been automatically assigned: 📁
|
Xunzhuo
force-pushed
the
docs/nvidia-dynamo-integration-proposal
branch
2 times, most recently
from
0364191 to
3761959
Compare
Signed-off-by: bitliu <[email protected]>
Xunzhuo
force-pushed
the
docs/nvidia-dynamo-integration-proposal
branch
from
be24cd5 to
5fabc12
Compare
rootfs
reviewed
Oct 8, 2025
| dynamics, competitive landscape, and stakeholder interests in your recommendations. | ||
| ``` | ||
|
|
||
| #### 2.2.2 Fusion Routing Strategy |
There was a problem hiding this comment.
is this integration depending on or can be continued by the prompt classification improvement?
There was a problem hiding this comment.
Nope i think it is not a blocker here.
rootfs
reviewed
Oct 8, 2025
|
|
||
| Semantic Router implements a **multi-signal fusion routing** approach that combines three complementary routing methods (as detailed in the [Prompt Classification Routing proposal](./prompt-classification-routing.md)): | ||
|
|
||
| **1. Keyword-Based Routing (Fast Path)** |
There was a problem hiding this comment.
this looks a potential for sub tasks in the integration.
rootfs
reviewed
Oct 8, 2025
| | Dimension | Semantic Router Alone | Dynamo Router Alone | **Integrated System** | | ||
| |-----------|----------------------|---------------------|----------------------| | ||
| | **Model Selection** | ✅ Semantic accuracy (14 categories) | ❌ No model awareness | ✅ Best model for task | | ||
| | **Worker Selection** | ❌ No worker awareness | ✅ KV cache optimization | ✅ Optimal worker for model | |
There was a problem hiding this comment.
i think #227 can help both model and worker selection
rootfs
reviewed
Oct 8, 2025
| |-----------|----------------------|---------------------|----------------------| | ||
| | **Model Selection** | ✅ Semantic accuracy (14 categories) | ❌ No model awareness | ✅ Best model for task | | ||
| | **Worker Selection** | ❌ No worker awareness | ✅ KV cache optimization | ✅ Optimal worker for model | | ||
| | **Prompt Engineering** | ✅ Domain-aware system prompts | ❌ No prompt optimization | ✅ Optimized CoT & MoE matching | |
There was a problem hiding this comment.
potentially the system prompt injection could impact the prefix cache, we should also monitor that
rootfs
approved these changes
Oct 8, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What type of PR is this?
docs: add NVIDIA Dynamo integration proposal