### What this PR does / why we need it?
1. Provide accuracy test report for development branch release.
2. Models and datasets for accuracy test：
| Model | datasets |
|---------------------------- | --------------------------- |
| Qwen2.5-7B-Instruct | ceval-val, gsm8k, mmlu |
| Qwen3-8B | ceval-val, gsm8k, mmlu |
| Llama-3.1-8B-Instruct | ceval-val, gsm8k, mmlu |
| Qwen2.5-VL-7B-Instruct | mmmu_val |
### Does this PR introduce _any_ user-facing change?
This PR will display the accuracy test report of the release versionin
docs/source/developer_guide/accuracy_report。
Qwen2.5-7B-Instruct.md
Qwen3-8B.md
Llama-3.1-8B-Instruct.md
Qwen2.5-VL-7B-Instruct .md
Signed-off-by: hfadzxy <starmoon_zhang@163.com>
### What this PR does / why we need it?
Update installation and tutorial doc
### Does this PR introduce _any_ user-facing change?
NO
### How was this patch tested?
preview
Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
Sometimes, user install a dev/editable version of vllm. In this case, we
should make sure vllm-ascend works as well.
This PR add a new env `VLLM_VERSION`. It's used for developers who edit
vllm. In this case, developers should set thie env to make sure which
vllm version is installed and used.
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
Fix pip install cmd in installation.md
Followup on: https://github.com/vllm-project/vllm-ascend/pull/661
### Does this PR introduce _any_ user-facing change?
No, doc only
### How was this patch tested?
Preview
Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
### What this PR does / why we need it?
The torch-npu 2.5.1 are published:
https://pypi.org/project/torch-npu/2.5.1/
It's time to remove all torch-npu dev version from vllm-ascend code base
### Does this PR introduce _any_ user-facing change?
Yes, using torch-npu 2.5.1
### How was this patch tested?
- [ ] CI passed
- [ ] Manually test
- [ ] Grep all `dev2025`
---------
Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
1. remove Chinese doc. The content is out of data and we don't have
enough time to maintain it.
2. Update feature support matrix. Refresh the content and add V1 status.
---------
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
Co-authored-by: Yikun Jiang <yikunkero@gmail.com>
Many users facing a failed installation when using `pip install -e .`,
this is mainly introduced by the released `torch-npu` version conflict
with `torch>=2.5.1`. This conflict mainly exist in the temp env of
pyproject build.
This pr updates installation tutorial by using `python setup.py develop`
to quick fix this.
cc @wangxiyuan
---------
Signed-off-by: MengqingCao <cmq0113@163.com>
### What this PR does / why we need it?
Add a `VLLMAscendQuantizer` to support w8a8 static (W8A8) and dynamic on
linear and moe (W8A8_DYNAMIC), the quantizer will be enable if a model
has [quantize
filed](https://huggingface.co/vllm-ascend/Qwen2.5-0.5B-Instruct-w8a8/blob/main/config.json#L27).
If MindIE Turbo is installed, the MindIE Turbo Quantizer will apply,
otherwise will use VLLMAscendQuantizer directly.
- This patch fix installation docs to make installation work
- This patch enable norm quantization by patch `RMSNorm.__init__`,
`RMSNorm.forward_oot`, `NPUModelRunnerBase.load_model`
- Add `AscendW8A8LinearMethod` for W8A8
- Add `AscendW8A8DynamicLinearMethod` and
`AscendW8A8DynamicFusedMoEMethod` for W8A8_DYNAMIC
- Add a e2e test for `vllm-ascend/Qwen2.5-0.5B-Instruct-w8a8`
### Does this PR introduce _any_ user-facing change?
Yes, support w8a8 quantization. After this patch supported, users can
use below commands to run w8a8 models:
```
vllm serve /root/.cache/modelscope/hub/Qwen/Qwen2.5-7B-Instruct-w8a8 --served-model-name "qwen2.5-7B"
```
### How was this patch tested?
0. CI passed: add e2e test for `vllm-ascend/Qwen2.5-0.5B-Instruct-w8a8`
1. From @Yikun:
I test Qwen2.5-0.5B-Instruct-w8a8 for functional test all is well, pls
refer to
https://github.com/vllm-project/vllm-ascend/pull/580#issuecomment-2816747613
2. From @dingdingchaomian :
Use qwen2.5-72b-instruct model and deepseek-v2-lite-chat tested, both
models were quantized using Ascend's msmodelslim tool:
- Qwen2.5-72b-instruct were tested twice, one for w8a8 static and one
for w8a8 dynamic.
- Deepseek-v2-lite-chat were tested once because its quantization used
both static and dynamic w8a8.
Models were tested using both off line inference and online serving, and
both work well. The inference codes are exactly the same with the
examples in
https://vllm-ascend.readthedocs.io/en/latest/quick_start.html, with
model path and tensor parallel number changed.
---------
Signed-off-by: dingdingchaomian <wangce21@huawei.com>
Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
Co-authored-by: dingdingchaomian <wangce21@huawei.com>
Co-authored-by: Angazenn <zengyanjia@huawei.com>
Co-authored-by: liujiaxu <liujiaxu4@huawei.com>
Co-authored-by: ApsarasX <apsarax@outlook.com>
Co-authored-by: ganyi1996ppo <pleaplusone.gy@gmail.com>
### What this PR does / why we need it?
Update v0.8.4 release note:
- Add contents for structured output feature.
- Remove redundant `(` in spec decoding.
### Does this PR introduce _any_ user-facing change?
NO
### How was this patch tested?
Preview
Signed-off-by: shen-shanshan <467638484@qq.com>
This PR added patch module for vllm
1. platform patch: the patch will be registered when load the platform
2. worker patch: the patch will be registered when worker is started.
The detail is:
1. patch_common: patch for main and 0.8.4 version
4. patch_main: patch for main verison
5. patch_0_8_4: patch for 0.8.4 version
1. install torch-npu before vllm-ascend to ensure custom ops build
success.
2. set `COMPILE_CUSTOM_KERNELS=0` if users want to disable custom ops
build.
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
This PR enable custom ops build by default.
### Does this PR introduce _any_ user-facing change?
Yes, users now install vllm-ascend from source will trigger custom ops
build step.
### How was this patch tested?
By image build and e2e CI
---------
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
Provide users with openEuler-based vllm images, so modify the quick
start readme
### Does this PR introduce _any_ user-facing change?
None
### How was this patch tested?
There is no need for performing any test.
---------
Signed-off-by: Icey <1790571317@qq.com>
### What this PR does / why we need it?
- Added instructions for verifying multi-node communication environment.
- Included explanations of Ray-related environment variables for
configuration.
- Provided detailed steps for launching services in a multi-node
environment.
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
manually tested.
Signed-off-by: jinyuxin <jinyuxin2@huawei.com>
### What this PR does / why we need it?
Add developer guide for using lm-eval
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
test manually
---------
Signed-off-by: hfadzxy <starmoon_zhang@163.com>
Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
Co-authored-by: Yikun Jiang <yikunkero@gmail.com>
### What this PR does / why we need it?
Add install system dependencies in install doc
Resolve:
```
$ pip install vllm==v0.7.3
CMake Error at CMakeLists.txt:14 (project):
No CMAKE_CXX_COMPILER could be found.
Tell CMake where to find the compiler by setting either the environment
variable "CXX" or the CMake cache entry CMAKE_CXX_COMPILER to the full path
to the compiler, or to the compiler name if it is in the PATH.
// ... ...
note: This error originates from a subprocess, and is likely not a problem with pip.
ERROR: Failed building wheel for vllm
Failed to build vllm
ERROR: Failed to build installable wheels for some pyproject.toml based projects (vllm)
```
Closes: https://github.com/vllm-project/vllm-ascend/issues/439
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
CI passed
Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
### What this PR does / why we need it?
Add developer guide for using OpenCompass
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
test manually
---------
Signed-off-by: hfadzxy <starmoon_zhang@163.com>
Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
Co-authored-by: Yikun Jiang <yikunkero@gmail.com>
1. remove useluss code in attention.py
2. multistep now using StatefulModelInputForNPU and do not use
StatefulModelInput
Signed-off-by: new-TonyWang <wangtonyyu222@gmail.com>
Add an example for user stories and fix some typo
Add a new section, user story in the docs, to collect user stories of
llvm-ascend, also add an example and the issue template to collect user
story
Signed-off-by: Zhenyu Zheng <zheng.zhenyu@outlook.com>
### 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>
### What this PR does / why we need it?
Add support for V1 Engine.
Please note that this is just the initial version, and there may be some
places need to be fixed or optimized in the future, feel free to leave
some comments to us.
### Does this PR introduce _any_ user-facing change?
To use V1 Engine on NPU device, you need to set the env variable shown
below:
```bash
export VLLM_USE_V1=1
export VLLM_WORKER_MULTIPROC_METHOD=spawn
```
If you are using vllm for offline inferencing, you must add a `__main__`
guard like:
```bash
if __name__ == '__main__':
llm = vllm.LLM(...)
```
Find more details
[here](https://docs.vllm.ai/en/latest/getting_started/troubleshooting.html#python-multiprocessing).
### How was this patch tested?
I have tested the online serving with `Qwen2.5-7B-Instruct` using this
command:
```bash
vllm serve Qwen/Qwen2.5-7B-Instruct --max_model_len 26240
```
Query the model with input prompts:
```bash
curl http://localhost:8000/v1/completions \
-H "Content-Type: application/json" \
-d '{
"model": "Qwen/Qwen2.5-7B-Instruct",
"prompt": "The future of AI is",
"max_tokens": 7,
"temperature": 0
}'
```
---------
Signed-off-by: shen-shanshan <467638484@qq.com>
Co-authored-by: didongli182 <didongli@huawei.com>
### What this PR does / why we need it?
Fix bugs of installation doc and format tool.
### Does this PR introduce _any_ user-facing change?
no.
### How was this patch tested?
no.
Signed-off-by: shen-shanshan <467638484@qq.com>
Run vllm-ascend on Single NPU
What this PR does / why we need it?
Add vllm-ascend tutorial doc for Qwen/Qwen2.5-VL-7B-Instruct model
Inference/Serving doc
Does this PR introduce any user-facing change?
no
How was this patch tested?
no
Signed-off-by: xiemingda <xiemingda1002@gmail.com>
### What this PR does / why we need it?
Fix `ValueError: Unrecognized distributed executor backend tp. Supported
values are 'ray', 'mp' 'uni', 'external_launcher' or custom ExecutorBase
subclass.`
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
Test on my local node
Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
### What this PR does / why we need it?
Re-arch on tutorials, move singe npu / multi npu / multi node to index.
- Unifiy docker run cmd
- Use dropdown to hide build from source installation doc
- Re-arch tutorials to include Qwen/QwQ/DeepSeek
- Make QwQ doc works
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
CI test
Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
