Skip to content

docs: Update README.md #2906

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
nvda-mesharma merged 1 commit into from
Sep 5, 2025
Merged

docs: Update README.md #2906

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@ limitations under the License.
[![Discord](https://dcbadge.limes.pink/api/server/D92uqZRjCZ?style=flat)](https://discord.gg/D92uqZRjCZ)
[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/ai-dynamo/dynamo)

| **[Roadmap](https://github.com/ai-dynamo/dynamo/issues/762)** | **[Documentation](https://docs.nvidia.com/dynamo/latest/index.html)** | **[Examples](https://github.com/ai-dynamo/dynamo/tree/main/examples)** | **[Design Proposals](https://github.com/ai-dynamo/enhancements)** |
| **[Roadmap](https://github.com/ai-dynamo/dynamo/issues/762)** | **[Support matrix](https://github.com/ai-dynamo/dynamo/blob/main/docs/support_matrix.md)** | **[Documentation](https://docs.nvidia.com/dynamo/latest/index.html)** | **[Examples](https://github.com/ai-dynamo/dynamo/tree/main/examples)** | **[Prebuilt containers](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-dynamo/collections/ai-dynamo)** | **[Design Proposals](https://github.com/ai-dynamo/enhancements)** | **[Blogs](https://developer.nvidia.com/blog/tag/nvidia-dynamo)**

# NVIDIA Dynamo

Expand Down Expand Up @@ -60,7 +60,7 @@ Dynamo is designed to be inference engine agnostic (supports TRT-LLM, vLLM, SGLa
| [**KV-Aware Routing**](/docs/architecture/kv_cache_routing.md) | ✅ | ✅ | ✅ |
| [**Load Based Planner**](/docs/architecture/load_planner.md) | 🚧 | 🚧 | 🚧 |
| [**SLA-Based Planner**](/docs/architecture/sla_planner.md) | ✅ | ✅ | 🚧 |
| [**KVBM**](/docs/architecture/kvbm_architecture.md) | 🚧 | 🚧 | 🚧 |
| [**KVBM**](/docs/architecture/kvbm_architecture.md) | ✅ | ✅ | 🚧 |
Copy link
Contributor

@coderabbitai coderabbitai bot Sep 5, 2025

Choose a reason for hiding this comment

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

💡 Verification agent

🧩 Analysis chain

Validate KVBM status across backends; add legend and define acronym on first mention

Ensure the table reflects actual support in vLLM/SGLang and in-progress state for TensorRT-LLM. Consider adding a legend for ✅/🚧 and expanding KVBM on first use to avoid ambiguity.

Repo-level verification:

Suggested additions right below the table:

> Legend: ✅ Available • 🚧 In progress

> KVBM: Briefly define the acronym here (expand the full term) and link to the design doc above.

🏁 Script executed:

#!/bin/bash
# Scan for KVBM references across backends to corroborate the matrix.
rg -nPi --hidden --glob '!**/node_modules/**' 'kvbm|kv[-_ ]?aware|kv block memory' -C2 components/ docs/ | sed 's/^/HIT: /'
echo "Note: absence of matches is not proof; check backend READMEs and features as needed."

Length of output: 41833

Update KVBM support matrix, add legend, define acronym

  • In README.md table row for KVBM, change statuses to: 🚧 for vLLM (WIP), ❌ for SGLang (Planned), 🚧 for TensorRT-LLM.
  • Add immediately below the table:

    Legend: ✅ Available • 🚧 In progress • ❌ Planned

  • On first mention, expand “KVBM” to “KV Block Manager (KVBM)”.
🧰 Tools
🪛 LanguageTool

[grammar] ~63-~63: There might be a mistake here.
Context: ...ure/kvbm_architecture.md) | ✅ | ✅ | 🚧 | To learn more about each framework and t...

(QB_NEW_EN)

🤖 Prompt for AI Agents 
In README.md around line 63, update the KVBM table row statuses to use the
requested symbols (set vLLM to 🚧, SGLang to ❌, TensorRT-LLM to 🚧), add a
legend line immediately below the table that reads "Legend: ✅ Available • 🚧 In
progress • ❌ Planned", and change the first occurrence of "KVBM" in the document
to "KV Block Manager (KVBM)". Ensure spacing and markdown table formatting
remain valid and the acronym expansion appears only on first mention.


To learn more about each framework and their capabilities, check out each framework's README!
- **[vLLM](components/backends/vllm/README.md)**
Expand Down
Loading