You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: docs/source/user_guide/release_notes.md
+22Lines changed: 22 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,5 +1,27 @@
1
1
# Release note
2
2
3
+
## v0.7.3rc2
4
+
5
+
This is 2nd release candidate of v0.7.3 for vllm-ascend. Please follow the [official doc](https://vllm-ascend.readthedocs.io/en/v0.7.3-dev) to start the journey.
6
+
- Quickstart with container: https://vllm-ascend.readthedocs.io/en/v0.7.3-dev/quick_start.html
- Add Ascend Custom Ops framewrok. Developers now can write customs ops using AscendC. An example ops `rotary_embedding` is added. More tutorials will come soon. The Custome Ops complation is disabled by default when installing vllm-ascend. Set `COMPILE_CUSTOM_KERNELS=1` to enable it. [#371](https://github.com/vllm-project/vllm-ascend/pull/371)
11
+
- V1 engine is basic supported in this release. The full support will be done in 0.8.X release. If you hit any issue or have any requirement of V1 engine. Please tell us [here](https://github.com/vllm-project/vllm-ascend/issues/414). [#376](https://github.com/vllm-project/vllm-ascend/pull/376)
12
+
- Prefix cache feature works now. You can set `enable_prefix_caching=True` to enable it. [#282](https://github.com/vllm-project/vllm-ascend/pull/282)
13
+
14
+
### Core
15
+
- Bump torch_npu version to dev20250320.3 to improve accuracy to fix `!!!` output problem. [#406](https://github.com/vllm-project/vllm-ascend/pull/406)
16
+
17
+
### Model
18
+
- The performance of Qwen2-vl is improved by optimizing patch embedding (Conv3D). [#398](https://github.com/vllm-project/vllm-ascend/pull/398)
19
+
20
+
### Other
21
+
22
+
- Fixed a bug to make sure multi step scheduler feature work. [#349](https://github.com/vllm-project/vllm-ascend/pull/349)
23
+
- Fixed a bug to make prefix cache feature works with correct accuracy. [#424](https://github.com/vllm-project/vllm-ascend/pull/424)
24
+
3
25
## v0.7.3rc1
4
26
5
27
🎉 Hello, World! This is the first release candidate of v0.7.3 for vllm-ascend. Please follow the [official doc](https://vllm-ascend.readthedocs.io/en/v0.7.3-dev) to start the journey.
0 commit comments