### What this PR does / why we need it?
Enable `ACL_OP_INIT_MODE=1` directly only when using V0 spec decode.
Find more details at **mengwei805**'s comment in
https://github.com/vllm-project/vllm-ascend/pull/1123.
### Does this PR introduce _any_ user-facing change?
The user will not be aware of `VLLM_ASCEND_ACL_OP_INIT_MODE`
(`ACL_OP_INIT_MODE`).
### How was this patch tested?
Test scripts:
```python
from vllm import LLM, SamplingParams
prompts = [
"The future of AI is",
]
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
llm = LLM(
model="Qwen/Qwen2.5-1.5B-Instruct",
tensor_parallel_size=1,
speculative_config={
"method": "ngram",
"num_speculative_tokens": 5,
"prompt_lookup_max": 4,
},
)
outputs = llm.generate(prompts, sampling_params)
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
```
Results:
```
Adding requests: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 76.70it/s]
Processed prompts: 100%|███████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 1.33it/s, est. speed input: 6.64 toks/s, output: 21.26 toks/s]
Prompt: 'The future of AI is', Generated text: ' bright\n\n04/15/2020\n\nBy: James'
```
---------
Signed-off-by: shen-shanshan <467638484@qq.com>
This PR added the unit test framework to enable ut for vLLM Ascend. Unit
test runs on CPU machines. It'll be ran once lint check is passed the
same as e2e test.
For unit test, this PR created a new folder called `ut` under `tests`
module. All the test file in `ut` should keep the same with the code in
`vllm-ascend`. The file name should be start with `test_` prefix. For
example, in this PR. the `test_ascend_config.py` is added for
`ascend_config.py` test.
A new fille `worker/test_worker_v1.py` is also added as the placeholder.
This file should be the unit test for `vllm-ascend/worker/worker_v1.py`.
Additional, a new `fake_weight` folder is added, it contains the
config.json from `facebook/opt-125m`, so that the test will not always
visit huggingface.
TODO:
We should add all the unit test file one by one in the future.
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
With this PR, we can migrate to the native `data_parallel.py` in vllm
examples and remove the version in vllm-ascend.
At present, `ASCEND_RT_VISIBLE_DEVICES` introduces considerable
difficulties; therefore, we must employ a temporary workaround and
manually specify the device.
Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
### What this PR does / why we need it?
Fix the bug in torch 2.5.1 that raising segment fault when enable
`pin_memory` while creating a tensor using `torch.tensor`.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
---------
Signed-off-by: shen-shanshan <467638484@qq.com>
Fix the ascend config check logic:
1. refactor check_ascend_config to make it clear:
1. torchair graph should not work with enforce_eager=True
2. aclgraph should not work with torchair graph
3. add refresh config for rlhf case
4. fix a typo in model runner
5. change expert_tensor_parallel_size default to 0 to keep the same as
before
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
More and more config options are added to additional_config. This PR
provide a new AscendConfig to manage these config options by an easier
way to make code cleaner and readable.
This PR also added the `additional_config` doc for users.
Added the test_ascend_config.py to make sure the new AscendConfig works
as expect.
TODO: Add e2e test with torchair and deepseek once the CI resource is
available.
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
When I run vllm-ascend, I get this error msg:
```bash
Traceback (most recent call last):
File "/home/sss/software/miniconda3/envs/vllm-v1/bin/vllm", line 8, in <module>
sys.exit(main())
File "/home/sss/github/vllm-project/vllm/vllm/entrypoints/cli/main.py", line 50, in main
cmd.subparser_init(subparsers).set_defaults(
File "/home/sss/github/vllm-project/vllm/vllm/entrypoints/cli/serve.py", line 101, in subparser_init
serve_parser = make_arg_parser(serve_parser)
File "/home/sss/github/vllm-project/vllm/vllm/entrypoints/openai/cli_args.py", line 254, in make_arg_parser
parser = AsyncEngineArgs.add_cli_args(parser)
File "/home/sss/github/vllm-project/vllm/vllm/engine/arg_utils.py", line 1582, in add_cli_args
current_platform.pre_register_and_update(parser)
File "/home/sss/github/vllm-project/vllm-ascend/vllm_ascend/platform.py", line 80, in pre_register_and_update
if ASCEND_QUATIZATION_METHOD not in quant_action.choices:
TypeError: argument of type 'NoneType' is not iterable
[ERROR] 2025-06-03-02:53:42 (PID:6005, Device:-1, RankID:-1) ERR99999 UNKNOWN applicaiton exception
```
This is because the `choices` attribute in `quant_action` can be `None`
and we don't check it.
```bash
# quant_action
_StoreAction(option_strings=['--quantization', '-q'], dest='quantization', nargs=None, const=None, default=None, type=<class 'str'>, choices=None, required=False, help='Method used to quantize the weights. If `None`, we first check the\n`quantization_config` attribute in the model config file. If that is\n`None`, we assume the model weights are not quantized and use `dtype` to\ndetermine the data type of the weights.', metavar=None)
```
Thus, I have added check for the `choices` to handle the scenario of
`choices=None`.
### Does this PR introduce _any_ user-facing change?
yes, vllm server with ascend quantization works now.
### How was this patch tested?
by `vllm server --quantization ascend` command.
Related: https://github.com/vllm-project/vllm/issues/19004
Signed-off-by: shen-shanshan <467638484@qq.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
Fix update_aclgraph_sizes when running MoE models.
---------
Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
### What this PR does / why we need it?
1. Implentment `NPUPiecewiseBackend` to enable aclgraph
2. Eable aclgraph by default in V1, but raise error when running
deepseek and raise warning when running models except for qwen
### How was this patch tested?
CI pass with the new ut
---------
Signed-off-by: MengqingCao <cmq0113@163.com>
### What this PR does / why we need it?
Revert the default value of enable_chunked_prefill to 'False' in
additional_scheduler_config. In engine v1, enable_chunked_prefill is
forcibly set to True in VllmConfig, which causes it to be perceived as
True in check_and_update_config(). As a result, when the v0 scheduler is
enabled, the chunked prefill feature remains active, leading to the
failure of the v0 scheduler and causing it to fall back to the native v1
scheduling logic.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
CI passed with new added/existing test.
Signed-off-by: rjg-lyh <1318825571@qq.com>
### What this PR does / why we need it?
Fix the bug of #703, where vllm wrong raised the ERROR : Failed to
import vllm_ascend_C:No module named 'vllm_ascend.vllm_ascend_C'. The
format for reporting import vllm_ascend_C failure is unified by warning
("Failed to import vllm_ascend_C:%s", e).
### Does this PR introduce _any_ user-facing change?
No
---------
Signed-off-by: yangpuPKU <604425840@qq.com>
### What this PR does / why we need it?
Fix the bugs when run deepseek model in engine v1.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
CI passed with new added/existing test.
---------
Signed-off-by: rjg-lyh <1318825571@qq.com>
For online serving, "ascend" quantization method is not a choice
natively, so we need to add "ascend" quantization method to quantization
methods list and the user can enable quantization using "vllm serve
--quantization ascend" command.
---------
Signed-off-by: 22dimensions <waitingwind@foxmail.com>
### What this PR does / why we need it?
Add padding for ACL Graph and refactor graph batch size adjustments to
utils.py
---------
Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
### What this PR does / why we need it?
Support the features of prefix cache and chunked prefill in v0/v1.
---------
Signed-off-by: rjg-lyh <1318825571@qq.com>
-->
### What this PR does / why we need it?
<!--
- Please clarify what changes you are proposing. The purpose of this
section is to outline the changes and how this PR fixes the issue.
If possible, please consider writing useful notes for better and faster
reviews in your PR.
- Please clarify why the changes are needed. For instance, the use case
and bug description.
- Fixes #
-->
1. Improve inference speed and usability for deepsek models with NPU
graph mode.
2. Modify some codes to adapt to CANN 8.1.RC1.beta1.
3. Add a switch for NPU graph mode and its cache.
### Does this PR introduce _any_ user-facing change?
<!--
Note that it means *any* user-facing change including all aspects such
as API, interface or other behavior changes.
Documentation-only updates are not considered user-facing changes.
-->
This PR provides an experimental configuration to enable NPU graph mode
for Deepseek models. User can set
additional_config={'enable_graph_mode': True} to try this feature. Note
that this feature currently only supports for V0 engine.
### How was this patch tested?
<!--
CI passed with new added/existing test.
If it was tested in a way different from regular unit tests, please
clarify how you tested step by step, ideally copy and paste-able, so
that other reviewers can test and check, and descendants can verify in
the future.
If tests were not added, please describe why they were not added and/or
why it was difficult to add.
-->
This patch was tested with the newest torch_npu 2.5.1
(https://pypi.org/project/torch-npu/#files) and CANN 8.1.RC1.beta1
toolkit&nnal&kernels
(https://www.hiascend.com/developer/download/community/result?module=cann)
released in 25/30 April.
Signed-off-by: linfeng-yuan <1102311262@qq.com>
Platform should only contain the function that based from vllm. This PR
move the unrelated function to the right place to make platform more
clear.
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
Deepseek v3 now adopt vanilla chunked prefill on MLA part which is
ineffcient for computing but necessary for chunked prefill. Since PR
https://github.com/vllm-project/vllm-ascend/pull/543 bring v0 scheduler
into vllm-ascend, we can now adopt torch_npu._npu_flash_attention inside
the mla backend for more performance boost. Also there are some
redundant computation inside the rope, which is also removed. This PR
should bring some performance gain for deepseek eager mode inference.
---------
Signed-off-by: ganyi <pleaplusone.gy@gmail.com>
### What this PR does / why we need it?
Enforce eager mode in the V1 engine ahead of the upcoming CANN and
torch_npu releases.
### Does this PR introduce _any_ user-facing change?
After this change, users will no longer need to manually set
enforce_eager=True.
### How was this patch tested?
Test it with regular offline inference examples.
Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
<!-- Thanks for sending a pull request!
BEFORE SUBMITTING, PLEASE READ
https://docs.vllm.ai/en/latest/contributing/overview.html
-->
### What this PR does / why we need it?
<!--
- Please clarify what changes you are proposing. The purpose of this
section is to outline the changes and how this PR fixes the issue.
If possible, please consider writing useful notes for better and faster
reviews in your PR.
- Please clarify why the changes are needed. For instance, the use case
and bug description.
- Fixes #
-->
This PR supports the access of vllm-acend to the piecewise_graph feature
provided by the v1 engine.
1. register unifiled_ascend_attention_with_output for piecewise_graph to
split graph.
2. support NPUGraph to accelerate kernel launch.
### Does this PR introduce _any_ user-facing change?
<!--
Note that it means *any* user-facing change including all aspects such
as API, interface or other behavior changes.
Documentation-only updates are not considered user-facing changes.
-->
support npugraph to default， Users can disenable the npugraph feature by
configuring enforce_eager.
This has corresponding requirements for the versions of torch_npu and
CANN, and they need to support graph capture.
### How was this patch tested?
<!--
CI passed with new added/existing test.
If it was tested in a way different from regular unit tests, please
clarify how you tested step by step, ideally copy and paste-able, so
that other reviewers can test and check, and descendants can verify in
the future.
If tests were not added, please describe why they were not added and/or
why it was difficult to add.
-->
it turn to default
---------
Signed-off-by: Bug Hunter Yan <yanpq@zju.edu.cn>
Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
Co-authored-by: Yizhou Liu <liu_yizhou@outlook.com>
### What this PR does / why we need it?
1. support deepseek with w8a8 quant;
2. support deepseek with mix-parallel(multi-DP, EP+TP);
3. support deepseek with graphmode.
---------
Signed-off-by: wen-jie666 <wenjie39@huawei.com>
Signed-off-by: Yizhou Liu <liuyizhou5@h-partners.com>
Signed-off-by: libaokui <libaokui@huawei.com>
Signed-off-by: linfeng-yuan <1102311262@qq.com>
Co-authored-by: wen-jie666 <wenjie39@huawei.com>
### What this PR does / why we need it?
This PR adds sleep mode feature for vllm-ascend, when sleeps, we do
mainly two things:
- offload model weights
- discard kv cache
RLHF tools(such as https://github.com/volcengine/verl and
https://github.com/OpenRLHF/OpenRLHF) have a strong need of sleep mode
to accelerate the training process.
This PR may solve #375 and #320 .
### Does this PR introduce _any_ user-facing change?
No existing user interfaces changed.
Users will have two new methods(`sleep()` and `wake_up()`) to use.
### How was this patch tested?
This PR is tested with Qwen/Qwen2.5-0.5B-Instruct.
At first, we have free NPU memory M1.
After `llm = LLM("Qwen/Qwen2.5-0.5B-Instruct", enable_sleep_mode=True)`
executed, we have free NPU memory M2. M2 < M1.
Then we call `llm.sleep(level=1)`, we have free NPU memory M3.
We have M3 > M2, M3 is very close to M1.
Plus, we have the same output tokens before sleep and after wake up,
with the config of `SamplingParams(temperature=0, max_tokens=10)` and
with the same input tokens of course.
This PR is utilizing the CMake procedure of #371 , thanks a lot.
Signed-off-by: Shuqiao Li <celestialli@outlook.com>
### What this PR does / why we need it?
Adopt custom kernel rotary embedding in actual model inference,
customized rotary_embedding will generate contiguous query and key in
the cpp side to reduce the overhead of two contiguous and index_select
compared with rotary_embedding in torch_npu. For now, rotary_embedding
can only support the scenario of `is_neox = true`, non-neox version rope
will be updated soon in the future.
---------
Signed-off-by: ganyi <pleaplusone.gy@gmail.com>
This PR adds AscendScheduler to vllm v1 engine.
This scheduler currently supports v0-style prefill-first scheduling
strategy.
In the future more schedule methods will be supported by this scheduler.
---------
Signed-off-by: hw_whx <wanghexiang7@huawei.com>
Co-authored-by: hw_whx <wanghexiang7@huawei.com>
### What this PR does / why we need it?
Remove `supports_structured_output()` in platform. This method is no need, because upstream has deleted this.
Signed-off-by: shen-shanshan <467638484@qq.com>
### 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?
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>
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>
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?
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>
### 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>
