### What this PR does / why we need it?
Adapt Disaggregated Prefill feature onto Ascend device
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
The test usage has been provided alongwith the PR, in
examples/offline_disaggregated_prefill_npu.py
To run it, do this
```
export PROMPT_DEVICE_ID=0,1
export DECODE_DEVICE_ID=2,3
python examples/offline_disaggregated_prefill_npu.py
```
---------
Signed-off-by: ZihuiQian <qianzihui@huawei.com>
Co-authored-by: ZihuiQian <qianzihui@huawei.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?
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?
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>
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?
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>
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 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?
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?
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>
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>
### What this PR does / why we need it?
Remove redundant `profile_run()` in model runner.
### Does this PR introduce _any_ user-facing change?
no.
### How was this patch tested?
no.
---------
Signed-off-by: Shanshan Shen <467638484@qq.com>
This PR added pooling support for vllm-ascend
Tested with `bge-base-en-v1.5` by encode:
```
from vllm import LLM
# Sample prompts.
prompts = [
"Hello, my name is",
"The president of the United States is",
"The capital of France is",
"The future of AI is",
]
# Create an LLM.
model = LLM(model="./bge-base-en-v1.5", enforce_eager=True)
# Generate embedding. The output is a list of EmbeddingRequestOutputs.
outputs = model.encode(prompts)
# Print the outputs.
for output in outputs:
print(output.outputs.embedding) # list of 4096 floats
```
Tested by embedding:
```
from vllm import LLM, SamplingParams
llm = LLM(model="./bge-base-en-v1.5", task="embed")
(output,) = llm.embed("Hello, my name is")
embeds = output.outputs.embedding
print(f"Embeddings: {embeds!r} (size={len(embeds)})")
```
Related: https://github.com/vllm-project/vllm-ascend/issues/200
## Known issue
The accuracy is not correct since this feature rely on `enc-dec`
support. It'll be done in the following PR by @MengqingCao
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
The rank returned by `torch.distributed.get_rank(device_group)` is the
local rank, but rank (or rank in process group (PG)) is expected.
Thus we change to use `torch.npu.current_device()` to set device
```python
# difference between `local_rank` and `rank_in_group`:
# if we have a group of size 4 across two nodes:
# Process | Node | Rank | Local Rank | Rank in Group
# 0 | 0 | 0 | 0 | 0
# 1 | 0 | 1 | 1 | 1
# 2 | 1 | 2 | 0 | 2
# 3 | 1 | 3 | 1 | 3
```
Tested by @wwfu109 with
`vllm/tests/distributed/test_customops::test_multi_process_tensor_parallel_pipeline_parallel`
Signed-off-by: MengqingCao <cmq0113@163.com>
### What this PR does / why we need it?
To avoid unnecessary delays, we only import torch_npu when profilling is
enabled.
Signed-off-by: wangli <wangli858794774@gmail.com>
### What this PR does / why we need it?
1. Fix cuda hard code in model runner.
2. Fix tutorials doc rendering error.
### Does this PR introduce _any_ user-facing change?
no.
### How was this patch tested?
no.
Signed-off-by: Shanshan Shen <467638484@qq.com>
### What this PR does / why we need it?
Remove unused assertion in `NPUWorker`, as this has been moved to
`Executor` in vLLM:
aabeb2688f/vllm/executor/uniproc_executor.py (L43)
### Does this PR introduce _any_ user-facing change?
N/A
### How was this patch tested?
CI passed with existing test.
Signed-off-by: MengqingCao <cmq0113@163.com>
### What this PR does / why we need it?
Remove padding for vlm inputs.
We don't need padding inputs now, this padding will break the input
preparetion of VLMs.
### Does this PR introduce _any_ user-facing change?
N/A
Signed-off-by: MengqingCao <cmq0113@163.com>
### What this PR does / why we need it?
The arg list of `Attention.forward()` is changed by
https://github.com/vllm-project/vllm/pull/13555.
The unused args `kv_caches` and `attn_metadata` are removed.
### Does this PR introduce _any_ user-facing change?
N/A
### How was this patch tested?
CI passed with existing test.
Signed-off-by: MengqingCao <cmq0113@163.com>
### What this PR does / why we need it?
Eliminate redundant operations in the code to improve performance
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
CI passed
---------
Signed-off-by: Yaphets24 <d_mym0618@163.com>
Signed-off-by: MengqingCao <cmq0113@163.com>
Co-authored-by: MengqingCao <cmq0113@163.com>
### What this PR does / why we need it?
In the case where `backend = ray`, only the main process completes the
`forward_oot` call, while the other worker processes call
`forward_native`. (This bug should also exist when `backend = mp`.)
### Does this PR introduce _any_ user-facing change?
no.
### How was this patch tested?
**Environment:**
CANN: 8.0.0
PyTorch: 2.5.1
Torch: 2.5.1rc1
python: 3.10
python: 3.10
vllm: branch main
vllm-ascend: branch main
The current implementation avoids the Ray Worker initialization issue,
as addressed in the
[PR](https://github.com/vllm-project/vllm-ascend/pull/92). Then, during
the `forward_oot` call, logging will be performed.
**Script:**
```bash
python examples/offline_distributed_inference_npu.py
```
**Result:**
```bash
NPURayWorkerWrapper pid=3984223) forward_oot run. #############################################
(NPURayWorkerWrapper pid=3984223) forward_oot run. #############################################
(NPURayWorkerWrapper pid=3984223) forward_oot run. #############################################
(NPURayWorkerWrapper pid=3984223) forward_oot run. #############################################
(NPURayWorkerWrapper pid=3984223) forward_oot run. #############################################
forward_oot run. #############################################
forward_oot run. #############################################
Processed prompts: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████| 4/4 [00:07<00:00, 1.96s/it, est. speed input: 2.80 toks/s, output: 51.00 toks/s]
Prompt: 'Hello, my name is', Generated text: ' Alex and I am a 16 year old male. I have been diagnosed with a rare genetic disorder called X-linked recessive. I have been told that I will not be able to have children. I have been told that I will not be able to have children because of the X-linked recessive disorder. I have been told that I will not be able to have children because of the X-linked recessive disorder. I have been told that I will not be able to have children because of'
Prompt: 'The president of the United States is', Generated text: ' Statesman. He is the leader of the country. He is the one who makes the decisions. He is the one who makes the laws. He is the one who makes the rules. He is the one who makes the country strong. He is the one who makes the country happy. He is the one who makes the country safe. He is the one who makes the country free. He is the one who makes the country beautiful. He is the one who makes the country great. He is'
Prompt: 'The capital of France is', Generated text: ' the city of Paris. It is the largest city in France and the second largest city in Europe. It is located in the center of the country, in the south of the country. It is situated on the banks of the Seine River, which flows through the city. The city is surrounded by the Alps and the Pyrenees mountains. The city is also surrounded by the Mediterranean Sea. The city is known for its beautiful architecture, its museums, its parks, and its food. Paris is'
Prompt: 'The future of AI is', Generated text: ' following the path of the internet, and the internet is following the path of the web. The web is a network of interconnected web pages, and the internet is a network of interconnected computers. The web is a network of interconnected computers, and the internet is a network of interconnected computers. The web is a network of interconnected computers, and the internet is a network of interconnected computers. The web is a network of interconnected computers, and the internet is a network of interconnected computers. The web is a network'
```
---------
Signed-off-by: Chenguang Li <757486878@qq.com>
In Model Runner, is_encoder_decoder is exacted from model_config to
determin whether vllm is running for enc-dec models. Obtaining this
status requires a long call stack, and the CPU overhead is high. So this
PR cache this status in __init__ of ModelInputForNPUBuilder.
Signed-off-by: hw_whx <wanghexiang7@huawei.com>
Co-authored-by: hw_whx <wanghexiang7@huawei.com>
### What this PR does / why we need it?
Add dispatch key for NPU, so that the log could be print correctly.
Now
```
executor_base.py:110] # CPU blocks: 220478, # CPU blocks: 21845
```
After this pr
```
executor_base.py:110] # NPU blocks: 220478, # CPU blocks: 21845
```
### Does this PR introduce _any_ user-facing change?
N/A
### How was this patch tested?
CI passed and log printed as above
Signed-off-by: MengqingCao <cmq0113@163.com>
### What this PR does / why we need it?
Changed default block_size in platform.py from 16 to 128, as Ascend
Devices have a better affinity for block size 128.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
CI passed
Signed-off-by: hzji210@gmail.com <hzji210@gmail.com>
