From 860531141ffac9861ad2b1ce2fd7df1dc51fd9bd Mon Sep 17 00:00:00 2001
From: 0oshowero0 <o0shower0o@outlook.com>
Date: Fri, 5 Jun 2026 10:44:52 +0800
Subject: [PATCH 1/2] update README & version files

Signed-off-by: 0oshowero0 <o0shower0o@outlook.com>
---
 README.md                      | 9 +++++----
 transfer_queue/version/version | 2 +-
 2 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/README.md b/README.md
index b28785eb..451ebafd 100644
--- a/README.md
+++ b/README.md
@@ -211,7 +211,7 @@ 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%">
 </p>
@@ -221,11 +221,12 @@ pip install TransferQueue
   <img src="https://github.com/TransferQueue/community_doc/blob/main/docs/performance_complex_0.1.6.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>
 
diff --git a/transfer_queue/version/version b/transfer_queue/version/version
index 4c6f32c3..699c6c6d 100644
--- a/transfer_queue/version/version
+++ b/transfer_queue/version/version
@@ -1 +1 @@
-0.1.8.dev0
+0.1.8

From c423543cba9a5d68af3bf94ef7a43513e295d9d5 Mon Sep 17 00:00:00 2001
From: 0oshowero0 <o0shower0o@outlook.com>
Date: Fri, 5 Jun 2026 11:31:45 +0800
Subject: [PATCH 2/2] update

Signed-off-by: 0oshowero0 <o0shower0o@outlook.com>
---
 README.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 451ebafd..b04a8316 100644
--- a/README.md
+++ b/README.md
@@ -213,12 +213,12 @@ pip install TransferQueue
 
 ### 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: 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.