[CI/Build][Doc] upgrade torch-npu to 0320 (#392)

### What this PR does / why we need it?
This pr upgrades torch-npu to 0320, so that #321,
https://github.com/vllm-project/vllm-ascend/issues/267#issuecomment-2745045743
could be fixed, and #372 should be reverted after this pr

### Does this PR introduce _any_ user-facing change?
upgrade torch-npu to 0320

### How was this patch tested?
tested locally with long seq inferencing.

---------

Signed-off-by: MengqingCao <cmq0113@163.com>

.github/workflows/vllm_ascend_test.yaml

@@ -124,7 +124,7 @@ jobs:
       - name: Install pta
         run: |
           cd /code/pta/
-          pip install ./torch_npu-2.5.1.dev20250308-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
+          pip install ./torch_npu-2.5.1.dev20250320-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
 
       - name: Run vllm-project/vllm-ascend test
         run: |

README.md

@@ -38,7 +38,7 @@ By using vLLM Ascend plugin, popular open-source models, including Transformer-l
 - Software:
   * Python >= 3.9
   * CANN >= 8.0.0
-  * PyTorch >= 2.5.1, torch-npu >= 2.5.1.dev20250308
+  * PyTorch >= 2.5.1, torch-npu >= 2.5.1.dev20250320
   * vLLM (the same version as vllm-ascend)
 
 ## Getting Started

README.zh.md

@@ -39,7 +39,7 @@ vLLM 昇腾插件 (`vllm-ascend`) 是一个由社区维护的让vLLM在Ascend NP
 - 软件：
   * Python >= 3.9
   * CANN >= 8.0.RC2
-  * PyTorch >= 2.5.1, torch-npu >= 2.5.1.dev20250308
+  * PyTorch >= 2.5.1, torch-npu >= 2.5.1.dev20250320
   * vLLM (与vllm-ascend版本一致)
 
 ## 开始使用

docs/source/developer_guide/versioning_policy.md

@@ -67,7 +67,7 @@ Following is the Release Compatibility Matrix for vLLM Ascend Plugin:
 
 | vllm-ascend  | vLLM         | Python | Stable CANN | PyTorch/torch_npu |
 |--------------|--------------| --- | --- | --- |
-| v0.7.3rc1 | v0.7.3 | 3.9 - 3.12 | 8.0.0   |  2.5.1 / 2.5.1.dev20250308 |
+| v0.7.3rc1 | v0.7.3 | 3.9 - 3.12 | 8.0.0   |  2.5.1 / 2.5.1.dev20250320 |
 | v0.7.1rc1 | v0.7.1 | 3.9 - 3.12 | 8.0.0   |  2.5.1 / 2.5.1.dev20250218 |
 
 ## Release cadence

docs/source/installation.md

@@ -12,7 +12,7 @@ This document describes how to install vllm-ascend manually.
     | Software     | Supported version | Note |
     | ------------ | ----------------- | ---- | 
     | CANN         | >= 8.0.0          | Required for vllm-ascend and torch-npu |
-    | torch-npu    | >= 2.5.1.dev20250308       | Required for vllm-ascend |
+    | torch-npu    | >= 2.5.1.dev20250320       | Required for vllm-ascend |
     | torch        | >= 2.5.1          | Required for torch-npu and vllm |
 
 You have 2 way to install:
@@ -159,14 +159,14 @@ Current version depends on a unreleased `torch-npu`, you need to install manuall
 # Here we take python 3.10 on aarch64 as an example. Feel free to install the correct version for your environment. See:
 #
 # https://pytorch-package.obs.cn-north-4.myhuaweicloud.com/pta/Daily/v2.5.1/20250308.3/pytorch_v2.5.1_py39.tar.gz
-# https://pytorch-package.obs.cn-north-4.myhuaweicloud.com/pta/Daily/v2.5.1/20250308.3/pytorch_v2.5.1_py310.tar.gz
+# https://pytorch-package.obs.cn-north-4.myhuaweicloud.com/pta/Daily/v2.5.1/20250320.3/pytorch_v2.5.1_py310.tar.gz
 # https://pytorch-package.obs.cn-north-4.myhuaweicloud.com/pta/Daily/v2.5.1/20250308.3/pytorch_v2.5.1_py311.tar.gz
 #
 mkdir pta
 cd pta
-wget https://pytorch-package.obs.cn-north-4.myhuaweicloud.com/pta/Daily/v2.5.1/20250308.3/pytorch_v2.5.1_py310.tar.gz
+wget https://pytorch-package.obs.cn-north-4.myhuaweicloud.com/pta/Daily/v2.5.1/20250320.3/pytorch_v2.5.1_py310.tar.gz
 tar -xvf pytorch_v2.5.1_py310.tar.gz
-pip install ./torch_npu-2.5.1.dev20250308-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
+pip install ./torch_npu-2.5.1.dev20250320-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
 ```
 ::::
 

pta_install.sh

@@ -2,14 +2,14 @@
 set -ex
 mkdir pta
 cd pta || exit
-wget https://pytorch-package.obs.cn-north-4.myhuaweicloud.com/pta/Daily/v2.5.1/20250308.3/pytorch_v2.5.1_py310.tar.gz
+wget https://pytorch-package.obs.cn-north-4.myhuaweicloud.com/pta/Daily/v2.5.1/20250320.3/pytorch_v2.5.1_py310.tar.gz
 tar -zxvf pytorch_v2.5.1_py310.tar.gz
 
 if [ "$(uname -i)" == "aarch64" ]
 then
-    pip install ./torch_npu-2.5.1.dev20250308-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
+    pip install ./torch_npu-2.5.1.dev20250320-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
 else
-    pip install ./torch_npu-2.5.1.dev20250308-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl --extra-index https://download.pytorch.org/whl/cpu/
+    pip install ./torch_npu-2.5.1.dev20250320-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl --extra-index https://download.pytorch.org/whl/cpu/
 fi
 
 cd ..

pytest.ini

@@ -37,6 +37,8 @@ norecursedirs =
     vllm-empty/tests/worker
     vllm-empty/tests/metrics
     vllm-empty/tests/neuron
+  ; fastsafetensors not support npu now
+    vllm-empty/tests/fastsafetensors_loader
 
 addopts = --ignore=vllm-empty/tests/test_utils.py
           --ignore=vllm-empty/tests/test_config.py