### What this PR does / why we need it?
Support MTP with：
- [x] V0 Scheduler
- [x] TorchAir
- [x] Single DP
- [x] Multi DP
- [x] Disaggregate PD
Known issues：
- [ ] Not support V1 Scheduler (chunked prefill), will be supported in a
few weeks
- [ ] vllm v0.10.0 does not support metrics with `DP > 1` right now,
need to comment out the line 171-175 in file
`vllm/vllm/v1/metrics/loggers.py`
```
if (len(self.engine_indexes) > 1
and vllm_config.speculative_config is not None):
raise NotImplementedError("Prometheus metrics with Spec Decoding "
"with >1 EngineCore per AsyncLLM is not "
"supported yet.")
```
To start an online server with torchair enabled, here is an example:
```
python -m vllm.entrypoints.openai.api_server \
--model="/weights/DeepSeek-R1_w8a8/" \
--trust-remote-code \
--max-model-len 40000 \
--tensor-parallel-size 4 \
--data_parallel_size 4 \
--max-num-seqs 16 \
--no-enable-prefix-caching \
--enable_expert_parallel \
--served-model-name deepseekr1 \
--speculative-config '{"num_speculative_tokens": 1, "method":"deepseek_mtp"}' \
--quantization ascend \
--host 0.0.0.0 \
--port 1234 \
--additional-config '{"ascend_scheduler_config":{"enabled":true,"enable_chunked_prefill":false},"torchair_graph_config":{"enabled":true,"graph_batch_sizes":[16]},"enable_weight_nz_layout":true}' \
--gpu_memory_utilization 0.9
```
offline example with torchair enabled
```
from vllm import LLM, SamplingParams
prompts = [
"Hello, my name is",
"The president of the United States is",
"The capital of France is",
"The future of AI is",
]
# Create a sampling params object.
sampling_params = SamplingParams(max_tokens=16, temperature=0)
# Create an LLM.
llm = LLM(
model="/home/data/DeepSeek-R1_w8a8/",
tensor_parallel_size=16,
max_num_seqs=16,
gpu_memory_utilization=0.9,
distributed_executor_backend="mp",
enable_expert_parallel=True,
speculative_config={
"method": "deepseek_mtp",
"num_speculative_tokens": 1,
},
trust_remote_code=True,
enforce_eager=False,
max_model_len=2000,
additional_config = {
'torchair_graph_config': {
'enabled': True,
"graph_batch_sizes": [16],
'enable_multistream_shared_expert': False,
},
"ascend_scheduler_config": {
"enabled": True
},
# 'expert_tensor_parallel_size': 16,
}
)
# Generate texts from the prompts.
# llm.start_profile()
outputs = llm.generate(prompts, sampling_params)
# llm.stop_profile()
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
```
- vLLM version: v0.10.0
- vLLM main:
302962e806
---------
Signed-off-by: xuyexiong <xuyexiong@huawei.com>
### What this PR does / why we need it?
Supports Deepseek-R1 w4a8 quantization.
Since R1 w4a8 uses mixed quantization, only the MOE layer uses
w4a8_dynamic quantization, so we added the w4a8_dynamic.py file, which
includes the AscendW4A8DynamicFusedMoEMethod class.
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
Adding ut case in `tests/ut/quantization/test_w4a8_dynamic.py` and
`tests/ut/quantization/test_quantizer.py`
Adding e2e case in
`tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_W4A8DYNAMIC`
to test deepseek w4a8_dynamic quantized model
#### 1.How to get weights using Modelslim
##### Installation steps
Use the branch master, the commit id is:
298e175d69b3b855111a1e09bbe2fcd12fdb4e24
git clone https://gitee.com/ascend/msit.git
cd msit/msmodelslim
bash install.sh
##### The required transformers environment
transformers>=4.48.2
##### Generate w4a8 weights
cd /example/DeepSeek
Command reference: msmodelslim/example/DeepSeek/README.md Execute the
[pre-check](https://gitee.com/ascend/msit/blob/master/msmodelslim/example/DeepSeek/README.md#%E8%BF%90%E8%A1%8C%E5%89%8D%E5%BF%85%E6%A3%80)
and [DeepSeek-R1 w4a8 mix
quantization](https://gitee.com/ascend/msit/blob/master/msmodelslim/example/DeepSeek/README.md#deepseek-r1-w4a8-%E6%B7%B7%E5%90%88%E9%87%8F%E5%8C%96%E5%89%8D%E4%B8%89%E5%B1%82-mlpw8a8-dynamic-%E9%87%8F%E5%8C%96mla%E5%85%B1%E4%BA%AB%E4%B8%93%E5%AE%B6w8a8%E9%87%8F%E5%8C%96%E8%B7%AF%E7%94%B1%E4%B8%93%E5%AE%B6w4a8-dynamic%E9%87%8F%E5%8C%96)
chapter
Reference command：python3 quant_deepseek_w4a8.py --model_path {Original
weight path} --save_path {Generate weight path} --mindie_format
##### Adapt to vllm-ascend
Since mindie_format generates mindie format, some adaptation
modifications are needed for vllm-ascend to use it:
`quant_model_description_w8a8_dynamic.json` rename to
`quant_model_description.json`, and add `"group_size": 256`
Modification in `config.json`：`"model_type":deepseekv2` is changed to
`"model_type":deepseek_v3`; `quantization_config` is removed;
tips:The group_size and weights match. If the w4a8 weights are not
generated using msmodelslim, you can check the group_size in
quantization_config in config.json.
#### 2.How to run w4a8
##### a.How to run eager mode
export VLLM_USE_V1=1 # v1
python -m vllm.entrypoints.openai.api_server --model=$1
--trust-remote-code -tp $2 -dp $3 --enable_expert_parallel
--quantization ascend --port $4 --max-model-len $5 --max-num-seqs $6
--enforce-eager
eg: python -m vllm.entrypoints.openai.api_server
--model=/weightpath/w4a8_4_layer --trust-remote-code -tp 4 -dp 4
--enable_expert_parallel --quantization ascend --port 8002
--max-model-len 5120 --max-num-seqs 128 --enforce-eager
##### b.How to run graph mode
export VLLM_USE_V1=1 # v1
export HCCL_BUFFSIZE=1024
python -m vllm.entrypoints.openai.api_server --model=$1
--trust-remote-code -tp $2 -dp $3 --enable_expert_parallel
--quantization ascend --port $4 --max-model-len $5
--additional_config='{"ascend_scheduler_config":{"enabled":true},"torchair_graph_config":{"enabled":true}}'
eg: python -m vllm.entrypoints.openai.api_server
--model=/weight/dsr1_w4a8_vllm --trust-remote-code -tp 4 -dp 4
--enable_expert_parallel --quantization ascend --port 8002
--max-model-len 5120
--additional_config='{"ascend_scheduler_config":{"enabled":true},"torchair_graph_config":{"enabled":true}}'
- vLLM version: v0.10.0
- vLLM main:
c494f96fbc
---------
Signed-off-by: Wang Kunpeng <1289706727@qq.com>
### What this PR does / why we need it?
Adding `W4A8_DYNAMIC` quantization support for linear.
Dense models like Qwen3 can infer with `W4A8_DYNAMIC` quantization.
### Does this PR introduce _any_ user-facing change?
None
### How was this patch tested?
Adding ut case in `tests/ut/quantization/test_w4a8_dynamic.py`
Adding e2e case in
`tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_Qwen3_W4A8DYNAMIC`
to test qwen3 w4a8_dynamic quantized model
Note the w4a8_dynamic quantized model is quantized by `msit/msmodelslim`
of commit `d0abb0a47e1f1a473b866ad41b737fbc28fb1409`
1. Generate `W4A8_DYNAMIC` quantization weights using `msmodelslim`
```shell
git clone https://gitee.com/ascend/msit.git
cd msit/msmodelslim
git checkout d0abb0a47e1f1a473b866ad41b737fbc28fb1409
bash install.sh
```
2. Serve model using `vllm`
```shell
VLLM_USE_V1=1 python -m vllm.entrypoints.openai.api_server \
--model vllm-ascend/Qwen3-8B-W4A8 \
--port 8000 \
--quantization ascend \
--tensor_parallel_size 2 \
--enforce-eager
```
- vLLM version: v0.10.0
- vLLM main:
4cd7fe6cea
---------
Signed-off-by: ZhouXiang <zhouxiang100@huawei.com>
Support the inference of the Deepseekr1-w8a8-mtp model with
statically-quantized shared_head in MTP layers.
- vLLM version: v0.9.2
- vLLM main:
6eca337ce0
Signed-off-by: curryliu <120010041@link.cuhk.edu.cn>
### What this PR does / why we need it?
support pangu moe w8a8c8
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
CI passed with new added test.
Signed-off-by: zhuyilin <809721801@qq.com>
### What this PR does / why we need it?
Add EPLB expert map import capabilities
### Does this PR introduce _any_ user-facing change?
When importing the EPLB expert map you need import expert map file by
vllm args additional_config
### How was this patch tested?
1.You need to collect expert hotness and generate an expert placement
file based on the hotness and the EPLB algorithm, or you can directly
use an existing expert placement table.
2.When launching vLLM, enable EC2 and pass the configuration via the
command-line argument:
--additional-config '{"expert_map_path": "/xxx/xxx/xx.json"}
Co-authored-by: songshanhu07 <1763685535@qq.com>
---------
Signed-off-by: songshanhu07 <1763685535@qq.com>
Signed-off-by: Yuxiao-Xu <664988918@qq.com>
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: songshanhu07 <1763685535@qq.com>
Co-authored-by: Xu Yuxiao <xuyuxiao2@huawei.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
Support MOE inner Multi-stream for Deepseek.
This feature requires graph mode with mc2 enabled.
---------
Signed-off-by: David9857 <985700846@qq.com>
### What this PR does / why we need it?
This PR fixes two accuracy bugs incurred by PR #819 when running
deepseekv3 series models:
1. #819 adds `all_to_all` communication in quantized cases, but
`all_gather` && `reduce_scatter` are removed in both of quantized and
unquantized cases. When running unquantized deepseekv3 models with
`ep_size == world_size`, the moe modules fail to communicate. Therefore,
this PR adds `all_to_all` communication on unquantized situation to
solve this accuracy issue.
2. Use `ep_size` rather than `dp_size` to decide whether to use
`all_to_all` in moe.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
CI passed with new added/existing test.
---------
Signed-off-by: angazenn <zengyanjia@huawei.com>
Co-authored-by: angazenn <zengyanjia@huawei.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>
<!-- 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?
1. This PR introduces native `all_to_all` communication operator to fix
`allgather` bugs when dp_size > 1. Besides, it adds a naive
implementation of force-load-balance when doing profile runs.
2. The operator `npu_dequant_swiglu_quant` only supports input
hidden_states with dtype `torch.int32`. This tensor occupies space of
`global_bs * seq_len * topk * hidden_size`, which might be very large as
`ep_size` grows. Therefore we need to disable this operator and use
original `swiglu` && `quantize`.
### 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>
make sure pytorch infer_schema check is patched before some case which
using fused moe ops:
1. model register
2. quantization loading
3. fused moe ut
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
After discussed with MindStudio about the quantization model format, we
decide to support another quant format which may used in new modelslim
tool, in which case, `quantization_config` may be removed from the
`config.json` file and `quant_model_description.json` will be used for
quantization configuration.
### Does this PR introduce _any_ user-facing change?
Yes, using the latest quantization format
### How was this patch tested?
Test locally
Signed-off-by: ganyi <pleaplusone.gy@gmail.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?
The pr will fix some bug about spec decode / MTP
The pr add a mtp e2e UT `test_mtp_correctness.py`
**vllm_ascend/attention/attention.py**
1. add support `self.attn_mask_cache` only has 1 element to cover scene
in which both spec docode and chunked prefill are enabled.
**vllm_ascend/distributed/parallel_state.py**
1. remove 2 assert because spec decode worker would use init_worker
twice
**vllm_ascend/models/deepseek_mtp.py**
1. remove unused params;
2. add support w8a8 in `CustomDeepSeekMTP`
**vllm_ascend/quantization/quant_config.py**
1. use `AscendUnquantizedFusedMoEMethod` instead of
`UnquantizedFusedMoEMethod`
**other**
1. replace `from vllm.logger import init_logger` to `from vllm.logger
import logger` all of the vllm-ascend project
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
Signed-off-by: mengwei805 <mengwei25@huawei.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?
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?
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>
