### What this PR does / why we need it?
Pre-construct a mask matrix to improve the efficiency of attention mask
construction during inference.
Note that the length of the matrix needs to be carefully balanced: a
matrix that is too large will consume excessive VRAM, while a matrix
that is too small will require dynamic concatenation during inference,
leading to performance degradation.
Therefore, an environment variable is added here to dynamically set the
size of the pre-constructed mask matrix based on requirements.
---------
Signed-off-by: shen-shanshan <467638484@qq.com>
Co-authored-by: didongli182 <didongli@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?
Fix CI by updating mypy and pining numpy version
_the modification of model_runner_v1 is just to make CI happy_
### Does this PR introduce _any_ user-facing change?
N/A
### How was this patch tested?
CI passed
Signed-off-by: MengqingCao <cmq0113@163.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>
### What this PR does / why we need it?
Add vLLM Ascend Weekly meeting link
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
Preview
Signed-off-by: Yikun Jiang <yikunkero@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?
We proposed the FastPatch method, which optimized patch embedding
(Conv3D) for Qwen2VL.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
We've tested it on benchmark, it meets our satisfaction and is better
than original patch_embed layer.
---------
Signed-off-by: baifanxxx <baifanxxx@gmail.com>
Signed-off-by: zouyida <zouyida@huawei.com>
Co-authored-by: zouyida <zouyida@huawei.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?
The purpose of this PR is to add benchmark scripts for npu, developers
can easily run performance tests on their own machines with one line of
code .
---------
Signed-off-by: wangli <wangli858794774@gmail.com>
1. Doc: Fix error link
2. Doc: make Chinese version the same with english
3. remove useless file `test.py`
4. update `collect_env.py`
5. Fix v1 import error
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
Add vLLM forum info and update readme
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
CI passed
---------
Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.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?
It fixes following bugs:
1. When searching a specific linear quantization implementation from a
tool (such as MindIE-Turbo), the mapping of packed linear is required to
identify correponding quant type.
2. The exception is narrowed down to ImportError when importing
MindIETurboQuantizer to better throw other errors.
3. The api of AscendKVCacheMethod.apply is aligned with that in
AscendAttentionBackendImpl.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
By performing offline inference:
---------
Signed-off-by: angazenn <zengyanjia@huawei.com>
Co-authored-by: angazenn <zengyanjia@huawei.com>
### What this PR does / why we need it?
Support encoder-only attention with torch sdpa
fix
https://github.com/vllm-project/vllm-ascend/pull/229#issuecomment-2695942741
### Does this PR introduce _any_ user-facing change?
N/A
### How was this patch tested?
Test locally with `pytest
vllm-project/vllm/tests/entrypoints/openai/test_score.py`
**Note**: Since torch compile on npu are still work in process, we need
to comment the following code to make UT run:
https://github.com/vllm-project/vllm/blob/main/vllm/model_executor/layers/vocab_parallel_embedding.py#L138
result:
```bash
/home/xxx/miniconda3/envs/atb/lib/python3.10/site-packages/pytest_asyncio/plugin.py:207: PytestDeprecationWarning: The configuration option "asyncio_default_fixture_loop_scope" is unset.
The event loop scope for asynchronous fixtures will default to the fixture caching scope. Future versions of pytest-asyncio will default the loop scope for asynchronous fixtures to function scope. Set the default fixture loop scope explicitly in order to avoid unexpected behavior in the future. Valid fixture loop scopes are: "function", "class", "module", "package", "session"
warnings.warn(PytestDeprecationWarning(_DEFAULT_FIXTURE_LOOP_SCOPE_UNSET))
================================================================================== test session starts ===================================================================================
platform linux -- Python 3.10.16, pytest-8.3.4, pluggy-1.5.0
rootdir: /home/xxx/code/vllm-cpu/vllm
configfile: pyproject.toml
plugins: shard-0.1.2, rerunfailures-15.0, asyncio-0.25.3, anyio-4.8.0, mock-3.14.0, forked-1.6.0, typeguard-4.3.0
asyncio: mode=strict, asyncio_default_fixture_loop_scope=None
collected 8 items
Running 8 items in this shard
tests/entrypoints/openai/test_score.py ........ [100%]
==================================================================================== warnings summary ====================================================================================
../../../miniconda3/envs/atb/lib/python3.10/site-packages/torch_npu/dynamo/torchair/__init__.py:8
/home/cmq/miniconda3/envs/atb/lib/python3.10/site-packages/torch_npu/dynamo/torchair/__init__.py:8: DeprecationWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html
import pkg_resources
-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
======================================================================== 8 passed, 1 warning in 131.42s (0:02:11) ========================================================================
```
This ut will be included in CI when torch compile feature is done.
Signed-off-by: MengqingCao <cmq0113@163.com>
### What this PR does / why we need it?
this pr fixes the error while inferring Qwen2_VL.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
We've tested it on benchmark, it meets our satisfaction and is equal to
gpu.
---------
Signed-off-by: zouyida <zouyida@huawei.com>
### What this PR does / why we need it?
Enable Expert-Parallel for ascend devices.
### Does this PR introduce _any_ user-facing change?
Enable EP
add `enable_expert_parallel=True` in your offline inference scripts,
like this:
```python
llm = LLM(
model="/path/to/model",
trust_remote_code=True,
tensor_parallel_size=4,
max_model_len=4096,
enforce_eager=True,
distributed_executor_backend="mp",
enable_expert_parallel=True,
)
```
### How was this patch tested?
Please use the `main` branch of vLLM.
---------
Signed-off-by: Yizhou Liu <liuyizhou5@h-partners.com>
Co-authored-by: Yizhou Liu <liuyizhou5@h-partners.com>
This PR changes the initial value of blocksize back to 128 and adds hash
value of request id list in model runner for implementing sampling param
cache in sampler.
Signed-off-by: hw_whx <wanghexiang7@huawei.com>
Co-authored-by: hw_whx <wanghexiang7@huawei.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>
### What this PR does / why we need it?
Pin modelscope<1.23.0 on vLLM v0.7.3 to resolve:
https://github.com/vllm-project/vllm/pull/13807
### 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?
Bump torch_npu version to dev20250308.3 to fix performance regression on
multi-stream case:
e04c580d07
.
### Does this PR introduce _any_ user-facing change?
NO
### How was this patch tested?
CI passed
Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
Update torch-npu version to fix torch npu exponential_ accuracy
With this update, the percision issue when setting `temperature > 0` is
fixed.
---------
Signed-off-by: Mengqing Cao <cmq0113@163.com>
### What this PR does / why we need it?
Add dispatch job to leverage jobs to dynamic devices include 2 stage as
below:
The dispatch job will spend extra about `10s * parallel number + 30s`
time to wait other job launch container and release lock.
- **Stage 1: Acquire lock**
add a dispatch job, this job use lockfile to acquire locks and then get
device number dynamically
- **Stage 2.1: Launch container with dynamic device**
pass the device number via output and start the container job with
dynamic device
- **Stage 2.2: Release lock**
once the job started, release the lock.
In the backend, we use multiple path to setup multiple self host runners
as load balancer:
```
$ pwd
/home/action
$ ll | grep actions
drwx------ 6 action action 4096 Mar 7 08:55 actions-runner-01
drwx------ 6 action action 4096 Mar 7 08:55 actions-runner-02
drwx------ 6 action action 4096 Mar 7 08:55 actions-runner-03
drwx------ 6 action action 4096 Mar 7 08:56 actions-runner-04
drwx------ 4 action action 4096 Jan 24 22:08 actions-runner-05
drwx------ 4 action action 4096 Jan 24 22:08 actions-runner-06
```
```
adduser -G docker action
su action
pip3 install docker prettytable
sudo yum install procmail
```
### Does this PR introduce _any_ user-facing change?
NO
### How was this patch tested?
- CI passed
- E2E test manully, triggered 3 jobs in parallel:
- [1st
job](https://github.com/vllm-project/vllm-ascend/actions/runs/13711345757/job/38348309297)
dispatch to /dev/davinci2.
- [2nd
job](https://github.com/vllm-project/vllm-ascend/actions/runs/13711348739/job/38348316250)
dispatch to /dev/davinci3
- [3rd
job](https://github.com/vllm-project/vllm-ascend/actions/runs/13711351493/job/38348324551)
dispatch to /dev/davinci4
Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
### What this PR does / why we need it?
1. It adds more description for classes in quant_config.py
2. It renames AscendQKVQuantAttentionMethod to AscendKVCacheMethod to
align with vLLM naming style.
3. It modifies the process when AscendLinearMethod or
AscendKVCacheMethod calls create_weights.
### Does this PR introduce _any_ user-facing change?
Yes. When creating weights, now AscendLinearMethod uses get_weight,
get_pertensor_param and get_perchannel_param api from linear quant
implementation, while AscendKVCacheMethod passes layer into linear quant
implementation.
### How was this patch tested?
By performing offline inference
---------
Signed-off-by: angazenn <zengyanjia@huawei.com>
Co-authored-by: angazenn <zengyanjia@huawei.com>
### What this PR does / why we need it?
Add initial FAQs
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
Preview
Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
This PR changes the shape of kv cache to avoid the view of k_cache and
v_cache.
What's more, cache the metadata of k_cache and v_cache to avoid
duplicative slice operations to improve performance.
Signed-off-by: hw_whx <wanghexiang7@huawei.com>
