[Bugfix] fix import error

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

Author: wangxiyuan

docs/source/conf.py

@@ -68,10 +68,10 @@
     # the branch of vllm-ascend, used in vllm-ascend clone and image tag
     # - main branch: 'main'
     # - vX.Y.Z branch: latest vllm-ascend release tag
-    'vllm_ascend_version': 'v0.9.0rc1',
+    'vllm_ascend_version': 'v0.9.0rc2',
     # the newest release version of vllm-ascend and matched vLLM, used in pip install.
     # This value should be updated when cut down release.
-    'pip_vllm_ascend_version': "0.9.0rc1",
+    'pip_vllm_ascend_version': "0.9.0rc2",
     'pip_vllm_version': "0.9.0",
     # CANN image tag
     'cann_image_tag': "8.1.rc1-910b-ubuntu22.04-py3.10",

docs/source/developer_guide/versioning_policy.md

@@ -22,6 +22,7 @@ Following is the Release Compatibility Matrix for vLLM Ascend Plugin:
 
 | vLLM Ascend | vLLM         | Python           | Stable CANN | PyTorch/torch_npu  | MindIE Turbo |
 |-------------|--------------|------------------|-------------|--------------------|--------------|
+| v0.9.0rc2   | v0.9.0       | >= 3.9, < 3.12   | 8.1.RC1     | 2.5.1 / 2.5.1      |              |
 | v0.9.0rc1   | v0.9.0       | >= 3.9, < 3.12   | 8.1.RC1     | 2.5.1 / 2.5.1      |              |
 | v0.8.5rc1   | v0.8.5.post1 | >= 3.9, < 3.12   | 8.1.RC1     | 2.5.1 / 2.5.1      |              |
 | v0.8.4rc2   | v0.8.4       | >= 3.9, < 3.12   | 8.0.0       | 2.5.1 / 2.5.1      |              |
@@ -34,6 +35,7 @@ Following is the Release Compatibility Matrix for vLLM Ascend Plugin:
 
 | Date       | Event                                     |
 |------------|-------------------------------------------|
+| 2025.06.10 | Release candidates, v0.9.0rc2             |
 | 2025.06.09 | Release candidates, v0.9.0rc1             |
 | 2025.05.29 | v0.7.x post release, v0.7.3.post1         |
 | 2025.05.08 | v0.7.x Final release, v0.7.3              |
@@ -71,6 +73,7 @@ Usually, each minor version of vLLM (such as 0.7) will correspond to a vLLM Asce
 | Branch     | Status       | Note                                 |
 |------------|--------------|--------------------------------------|
 | main       | Maintained   | CI commitment for vLLM main branch and vLLM 0.9.x branch   |
+| v0.9.1-dev | Maintained   | CI commitment for vLLM 0.9.0 and 0.9.1 version |
 | v0.7.3-dev | Maintained   | CI commitment for vLLM 0.7.3 version |
 | v0.7.1-dev | Unmaintained | Replaced by v0.7.3-dev               |
 

docs/source/user_guide/graph_mode.md

@@ -54,7 +54,7 @@ outputs = model.generate("Hello, how are you?")
 online example:
 
 ```shell
-vllm serve Qwen/Qwen2-7B-Instruct --additional-config='{"torchair_graph_config": {"enable": True}}'
+vllm serve Qwen/Qwen2-7B-Instruct --additional-config='{"torchair_graph_config": {"enable": true}}'
 ```
 
 You can find more detail about additional config [here](./additional_config.md)

docs/source/user_guide/release_notes.md

@@ -1,5 +1,13 @@
 # Release note
 
+## v0.9.0rc1 - 2025.06.10
+
+This release contains some quick fixes for v0.9.0rc1. Please use this release instead of v0.9.0rc1.
+
+### Highlights
+
+- Fix the import error when vllm-ascend is installed without editable way. [#1152](https://github.com/vllm-project/vllm-ascend/pull/1152)
+
 ## v0.9.0rc1 - 2025.06.09
 
 This is the 1st release candidate of v0.9.0 for vllm-ascend. Please follow the [official doc](https://vllm-ascend.readthedocs.io/en/) to start the journey. From this release, V1 Engine is recommended to use. The code of V0 Engine is frozen and will not be maintained any more. Please set environment `VLLM_USE_V1=1` to enable V1 Engine.

vllm_ascend/compilation/__init__.py

@@ -496,7 +496,11 @@ def _update_states(self, scheduler_output: "SchedulerOutput") -> None:
             # Update the block IDs.
             if not req_data.resumed_from_preemption:
                 # Append the new blocks to the existing block IDs.
-                req_state.block_ids.extend(req_data.new_block_ids)
+                for block_ids, new_block_ids in zip(  # type: ignore[call-overload]
+                        req_state.block_ids,
+                        req_data.new_block_ids,
+                        strict=True):
+                    block_ids.extend(new_block_ids)
             else:
                 # The request is resumed from preemption.
                 # Replace the existing block IDs with the new ones.