### What this PR does / why we need it?
Qwen3 MoE supports SP. In scenarios like AlltoAll, AlltoAllv, and MC2,
replacing AllReduce with Reduce-Scatter and AllGather achieves
computational benefits in norm operations while saving one AllGather
communication. This feature is enabled during the P-phase and delivers
notable gains in long-sequence scenarios (e.g., 16k–25k), with
performance improvements reaching 5%–10%.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
```
compilation_config={
"pass_config":{
"enable_sequence_parallelism": True
}
},
enable_expert_parallel=True,
```
- vLLM version: v0.10.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/9edd1db02bc6dce6da503503a373657f3466a78b
---------
Signed-off-by: libaokui <libaokui@huawei.com>
Co-authored-by: libaokui <libaokui@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:
https://github.com/vllm-project/vllm/commit/c494f96fbcf5e9f19f59e3dea6c2780aeb6c567f
---------
Signed-off-by: Wang Kunpeng <1289706727@qq.com>
### What this PR does / why we need it?
Fixes unable to load `qwen3_moe` quantized weights issue due to #1994
### Does this PR introduce _any_ user-facing change?
None
### How was this patch tested?
Add a `qwen3_moe` W8A8 quantized model in
`tests/e2e/multicard/test_qwen3_moe.py`
- vLLM version: v0.10.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/c494f96fbcf5e9f19f59e3dea6c2780aeb6c567f
---------
Signed-off-by: zhoux77899 <zhouxiang100@huawei.com>
### What this PR does / why we need it?
Fix Qwen MoE accuracy bug in DP scenario.
Now the implentment of `FusedMoE` in vLLM use `All2AllManager` to
manager different all2all algorithm branch. And the default branch use
`Multicast` in `dispatch` phase and `all_reduce` in `combine` phase,
which are not implented in vLLM-Ascend. This leading to invoking into a
default implentment in `base_communicator`, with empty `dispatch` and
`combine` operations, thus causing the accuracy issue on it.
This pr is a temporary workaround, refacting all2all in vLLM-Ascend
could be a better way.
- vLLM version: v0.10.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/ad57f23f6a528ab01066998b41796a44340fd43d
---------
Signed-off-by: MengqingCao <cmq0113@163.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:
https://github.com/vllm-project/vllm/commit/4cd7fe6ceaf5ad7d8ac2ba5597cd964c6db7e306
---------
Signed-off-by: ZhouXiang <zhouxiang100@huawei.com>
### What this PR does / why we need it?
1.Fixed the issue that pyhccl e2e cannot run continuously with other
tests.
2.Cleaned up the resources occupied by the dynamic_npugraph_batchsize
e2e test.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
This is a e2e test
e2e multi-cards tests local running successfully.
- vLLM version: v0.9.2
- vLLM main:
https://github.com/vllm-project/vllm/commit/0df4d9b06b15fa39eeb2d440e7742da93afd5e6c
Signed-off-by: leo-pony <nengjunma@outlook.com>
### What this PR does / why we need it?
Currently our workflow run time takes about 3 hours in total, which
seriously affects the developer experience, so it is urgent to have a
optimization, after this pr, It is expected that the running time of the
full CI can be shortened to 1h40min.
- Enable linux-aarch64-a2 (64GB) to replace linux-arm64-npu (32GB)
- Change TP4 ---> TP2 * 2 max-parallel
- Move DeepSeek-V2-Lite-W8A8 to single card test
### Does this PR introduce _any_ user-facing change?
No
- vLLM version: v0.10.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/a2480251ec92ba2a849464dde48db8a2b7f6ef81
---------
Signed-off-by: wangli <wangli858794774@gmail.com>
### What this PR does / why we need it?
Support pipeline parallel with ray backend in V1Engine.
Fixes#1751
### Does this PR introduce _any_ user-facing change?
Users could specify ray as distributed backend when inferencing with pp
### How was this patch tested?
CI passed with new added test.
- vLLM version: v0.9.2
- vLLM main:
https://github.com/vllm-project/vllm/commit/32142b3c62277ac7cb941f2036270decb6b514f4
---------
Signed-off-by: MengqingCao <cmq0113@163.com>
### What this PR does / why we need it?
Optimizes the performance of the Qwen3 quantization model by registering
a custom model and adding the AddRmsNormQuant operation. Subsequent PRs
will focus on performance optimizations based on this custom model.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
CI passed with existing test.
- vLLM version: v0.9.2
- vLLM main:
https://github.com/vllm-project/vllm/commit/8d0a01a5f2b53794e4bc6b734d7b63cb8a9b7d7d
Signed-off-by: rjg-lyh <1318825571@qq.com>
### What this PR does / why we need it?
Unify Model Usage via ModelScope
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
CI passed
Signed-off-by: hfadzxy <starmoon_zhang@163.com>
### What this PR does / why we need it?
This PR supports torchair graph mode with non-mla backend on both 800IA2
and 300I Duo platforms. The main change is to add
`attention_v1_torchair.py` to support specific attention related
operations that are required by torchair.
### Does this PR introduce _any_ user-facing change?
Before this PR, vLLM-Ascend only allows deepseek to use torchair. Now we
can also use it with pangu. Besides, we add a support model list to
control which type of models that can use torchair.
### How was this patch tested?
We have test it with PanguProMoE on both 800IA2 and 300I Duo platforms,
and model generates answer normally.
---------
Signed-off-by: angazenn <zengyanjia@huawei.com>
Signed-off-by: tianyitang <tangtianyi4@huawei.com>
Co-authored-by: angazenn <zengyanjia@huawei.com>
Co-authored-by: tianyitang <tangtianyi4@huawei.com>
### What this PR does / why we need it?
Add test for chunked prefill and prefix cache on v1/AscendScheduler
Covered scenarios:
- `Qwen/Qwen3-0.6B-Base` and `deepseek-ai/DeepSeek-V2-Lite-Chat` ---
multicard CI time increased by 19 min
- `V1 + default scheduler` vs `V1 + default scheduler + enable prefix
cache`
- `V1 + Ascend scheduler` vs `V1 + Ascend scheduler + enable prefix
cache` vs `V1 + Ascend scheduler + enable prefix cache + enable chunked
prefill`
- `Qwen/Qwen3-0.6B-Base` --- singlecard CI time increased by 8 min
- `V1 + Ascend scheduler` vs `V1 + Ascend scheduler + enable chunked
prefill`
should rebase after #1498 and #1446
### Does this PR introduce _any_ user-facing change?
N/A
### How was this patch tested?
CI passed with new added test.
Signed-off-by: MengqingCao <cmq0113@163.com>
Previous, the DeepSeek V3 Pruning weight is not correct, the moe layer
is not tested. We update a new Pruning model to enable moe layer
compute.
This PR fix the CI to address the new weight.
---------
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
After #1094, decode might be executed with non-compiled mode, despite of
`torchair_graph_config.enabled`, causing multistream mla to fail, which
assumes torchair compiled mode for decode when
`torchair_graph_config.enabled == True`.
Augment that assumption to fix this.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Tested both offline, and by graph mode mla e2e testcase.
---------
Signed-off-by: sdmyzlp <lrwei2@petalmail.com>
### What this PR does / why we need it?
Add `max_num_tokens_across_dp` to AscendMetadata to fix dp
This pr fixes the bug introduced by
https://github.com/vllm-project/vllm-ascend/pull/1229, which add an arg
`max_num_tokens_across_dp` when dp_size > 1.
Signed-off-by: MengqingCao <cmq0113@163.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>