Skip to content

[chore] Update README & bump version from 0.1.8.dev0 to 0.1.8 #118

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
0oshowero0 merged 2 commits into from
Jun 8, 2026
+8 −7
Merged

[chore] Update README & bump version from 0.1.8.dev0 to 0.1.8 #118

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8605311
update README & version files
0oshowero0 Jun 5, 2026
c423543
update
0oshowero0 Jun 5, 2026
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
13 changes: 7 additions & 6 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -211,21 +211,22 @@ pip install TransferQueue

<h2 id="performance">📊 Performance</h2>

### Simple Case: Regular Tensor Only
### Simple Case: Regular Tensor
<p align="center">
<img src="https://github.com/TransferQueue/community_doc/blob/main/docs/performance_simple_0.1.6.png?raw=true" width="100%">
<img src="https://github.com/TransferQueue/community_doc/blob/main/docs/performance_simple_0.1.8.png?raw=true" width="100%">
</p>

### Complex Case: Regular Tensor + NestedTensor + NonTensor
<p align="center">
<img src="https://github.com/TransferQueue/community_doc/blob/main/docs/performance_complex_0.1.6.png?raw=true" width="100%">
<img src="https://github.com/TransferQueue/community_doc/blob/main/docs/performance_complex_0.1.8.png?raw=true" width="100%">
</p>

> Note: Optimization for MooncakeStore and other backends are still in process. Warmly welcome contributions from the community!
> Note: The openYuanrong benchmark uses only a single NPU, so it doesn't reflect multi-NPU scalability. Additionally, openYuanrong was tested on a different hardware setup than the other backends.

For detailed performance benchmarks, please refer to [this blog](https://www.yuque.com/haomingzi-lfse7/lhp4el/tml8ke0zkgn6roey?singleDoc#).
For detailed performance benchmarks, please refer to [the full benchmark report](https://www.yuque.com/haomingzi-lfse7/lhp4el/mywsxovevynra42u?singleDoc#).

We also provide a [stress test report](https://www.yuque.com/haomingzi-lfse7/lhp4el/mt0vedqy7c337pgg?singleDoc#) that demonstrates more than **8192 concurrent clients writing 2 TB of data** into TransferQueue across 4 nodes. The system remains stable without any crashes or data loss.
### Stress Test
Beyond throughput, we also validated stability under high concurrency. We provide a [stress test report](https://www.yuque.com/haomingzi-lfse7/lhp4el/mt0vedqy7c337pgg?singleDoc#) that demonstrates more than **8192 concurrent clients writing 2 TB of data** into TransferQueue across 4 nodes. The system remains stable without any crashes or data loss.

<h2 id="customize"> 🛠️ Customize TransferQueue</h2>

Expand Down
2 changes: 1 addition & 1 deletion transfer_queue/version/version
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1 @@
0.1.8.dev0
0.1.8
Loading