Commit Graph
59 Commits
Author SHA1 Message Date
Mengqing Cao 4ff422c730 [CI][Bugfix] Quickfix for DPMetaData (#3234)
### What this PR does / why we need it?
Fix `dpmetadata` and `Qwen3MoeSparseMoeBlock` break introduced by
https://github.com/vllm-project/vllm/commit/26a7a33b88e38c45680aa6002b9d6e27875a39a3#diff-c1550d0a38469d039370567d8981969530cbfffc7302cd1778e7c2c8a9322dea

NOTE: we maintain a different sp in vllm-ascend with vllm, thus we can
just use `cu_tokens_across_sp(1)` as `cu_tokens_across_dp_cpu`

close https://github.com/vllm-project/vllm-ascend/issues/3236,
https://github.com/vllm-project/vllm-ascend/issues/3239
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?


- vLLM version: v0.10.2
- vLLM main:
https://github.com/vllm-project/vllm/commit/releases/v0.11.0

---------

Signed-off-by: MengqingCao <cmq0113@163.com>
2025-09-28 21:11:22 +08:00
florenceCHandflorenceCH 14497b748d Remove qwen3 moe MC2 cumsum & cast (#3126)
What this PR does / why we need it?
The Qwen3 moe MC2 graph currently has two redundant computational
operator implementations. After npu_moe_distribute_dispatch_v2, the
cumsum and cast operations have been added. By using
expert_token_nums_type=0 and not converting weight_scale to float32,
these two operators can be eliminated, thereby improving inference
performance.

Does this PR introduce any user-facing change?
No

How was this patch tested?
No need

vLLM version: v0.10.2
vLLM main:
https://github.com/vllm-project/vllm/commit/f225ea7dd98e9f29752e5c032cd4a8ee1d712f16

- vLLM version: v0.10.2
- vLLM main:
https://github.com/vllm-project/vllm/commit/f225ea7dd98e9f29752e5c032cd4a8ee1d712f16

---------

Signed-off-by: florenceCH <gaoxiang120@huawei.com>
Co-authored-by: florenceCH <gaoxiang120@huawei.com>
2025-09-26 08:51:30 +08:00
wangxiyuan ac1c2cd9ac [CI] Upgrade vllm version - 0925 (#3167)
Upgrade vLLM to newest commit.

1. Remove the useless func get_state_cls, it has been removed from vLLM
already.
https://github.com/vllm-project/vllm/commit/e6750d0b18e07631bb2ea7f256f7dd444d4936fa
2. Fix ut broken by
https://github.com/vllm-project/vllm/commit/6160ba4151084c78164a0f472ce4da04067f9705


- vLLM version: v0.10.2
- vLLM main:
https://github.com/vllm-project/vllm/commit/b1068903fdca26cf6b4a1a51a32c3365ce3ac636

---------

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
2025-09-25 14:20:10 +08:00
wangxiyuanandMengqingCao a055183821 [CI] Upgrade vLLM version (#3139)
Upgrade vLLM version to the newest commit.
- Fix the break change introduced by
https://github.com/vllm-project/vllm/commit/969b4da3a6ab737f72cb33db502b4c0bb70d4139
- Add a patch to quick fix torhcair
https://github.com/vllm-project/vllm/commit/de94289a98d7ec52a5ef02719e01a1db8b505170
- fix the ut error introduced by
https://github.com/vllm-project/vllm/commit/de94289a98d7ec52a5ef02719e01a1db8b505170

Close: https://github.com/vllm-project/vllm-ascend/issues/3138


- vLLM version: v0.10.2
- vLLM main:
https://github.com/vllm-project/vllm/commit/f225ea7dd98e9f29752e5c032cd4a8ee1d712f16

---------

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Signed-off-by: MengqingCao <cmq0113@163.com>
Co-authored-by: MengqingCao <cmq0113@163.com>
2025-09-25 07:36:51 +08:00
weichenandweijinqian0 37a0715eda [Refactor] Adjustments to moe_comm_method selection process (#3001)
### What this PR does / why we need it?
Fix issues mentioned in
https://github.com/vllm-project/vllm-ascend/pull/2791 and some minor
refactoring.
1. Use Enum instead of string.
2. Avoid setting a new property to forward_context in
AscendFusedMoE.forward().
3. Enabling TokenDispatcherWithMoge.
4. Remove redundant code.

### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?

Qwen3-30B-A3B/Qwen3-30B-A3B-W8A8/DeepSeek-V3-W4A8-Pruing/deepseek-mtp/pangu-pro-moe-pruing:
1. Enable/Disable EP
2. Aclgraph & eager


- vLLM version: v0.10.2
- vLLM main:
https://github.com/vllm-project/vllm/commit/9607d5eb449711b349d4c2bee0a9c94afcc7ed14

Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
Co-authored-by: weijinqian0 <12153182+weijinqian0@users.noreply.github.com>
2025-09-22 19:12:58 +08:00
Li WangandMengqingCao 12bcbd02bb [CI] Upgrade vLLM to 20250919 (6d8246aa) and fix some broken issue (#2907)
### What this PR does / why we need it?
1. This pr bump vllm commit to
https://github.com/vllm-project/vllm/commit/6d8246aaffff3ebec84767e373212a7b8da328e2
2. fix upstream changes https://github.com/vllm-project/vllm/pull/24548
abort multi-modal kwargs, make vllm main and `v0.10.2` both adaptable
3. fix metadata_builder changes introduced by
https://github.com/vllm-project/vllm/pull/23693
4. fix `structured_outputs_config` changes introduced by
https://github.com/vllm-project/vllm/pull/22772
5. fix `moe_config` changes introduced by
https://github.com/vllm-project/vllm/pull/22537

Co-authored-by:  MengqingCao <cmq0113@163.com>
Co-authored-by:  Yikun Jiang <yikunkero@gmail.com>


- vLLM version: v0.10.2
- vLLM main:
https://github.com/vllm-project/vllm/commit/c60e6137f0bf2034853919b3a9d705d7e06b93cf

---------

Signed-off-by: wangli <wangli858794774@gmail.com>
Signed-off-by: MengqingCao <cmq0113@163.com>
Co-authored-by: MengqingCao <cmq0113@163.com>
2025-09-20 17:37:57 +08:00
whx 0a526768f5 [Feature] Support moe multi-stream for aclgraph. (#2946)
This PR puts the calculation of shared experts into a separate stream,
overlaping with routing experts.

- vLLM version: v0.10.2
- vLLM main:
https://github.com/vllm-project/vllm/commit/fbd6523ac00082c398dc8126434cede595169609

---------

Signed-off-by: whx-sjtu <2952154980@qq.com>
2025-09-19 11:06:45 +08:00
Icey acb46f303f Fix VocabParallelEmbedding UT (#2722)
### What this PR does / why we need it?
Fix VocabParallelEmbedding UT

### How was this patch tested?
CI passed with new added/existing test.

- vLLM version: main
- vLLM main:
https://github.com/vllm-project/vllm/commit/f592b3174b39a7aeac52432d66d76e89ff0a80b4

---------

Signed-off-by: Icey <1790571317@qq.com>
2025-09-18 19:54:01 +08:00
realliujiaxuandweijinqian0 af2a886814 refactor linear (#2867)
### What this PR does / why we need it?
The current linear.py has the following issues:

- There is redundant conditional logic in the `comm_group` and `forward`
selection for classes such as `AscendMergedColumnParallelLinear`.

- Inconsistent comm_group selection logic exists among
`AscendMergedColumnParallelLinear`, `AscendColumnParallelLinear`, and
`AscendQKVParallelLinear`.

To address these two issues, this PR encapsulates `comm_group` and
`forward` into classes and extracts the classes selection logic into
common functions. For future additions of custom communication groups or
forward methods, it will only be necessary to extend
`CustomColumnParallelOp` or `CustomRowParallelOp` and add new selection
logic.

### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?


- vLLM version: v0.10.2
- vLLM main:
https://github.com/vllm-project/vllm/commit/dd39baf7175c5e79faef071c67bb318eadb7752f

---------

Signed-off-by: realliujiaxu <realliujiaxu@163.com>
Co-authored-by: weijinqian0 <weijinqian@huawei.com>
2025-09-18 14:09:19 +08:00
rjg-lyh 6b7117dbb7 [main] addrmsnorm + quant fusion optim in Dense Models (#2772)
### What this PR does / why we need it?
This PR fused addrmsnorm op and w8a8 quant op to get better perf.

### Does this PR introduce _any_ user-facing change?
No.

### How was this patch tested?
CI passed with new added/existing test.

- vLLM version: v0.10.2
- vLLM main:
https://github.com/vllm-project/vllm/commit/0faf3cc3e84a83bac56492d297f2c9909fec7de9

Signed-off-by: rjg-lyh <1318825571@qq.com>
2025-09-16 22:31:38 +08:00
1c5900327b [refactor] refactor deepseek-related files (#2849)
### What this PR does / why we need it?
This PR deletes ~2K lines of code about deepseek modeling. It falls back
CustomDeepseekV2 modules to original vllm implementations and adapts
some modifications in vllm about deepseek and moe.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
E2E  vllm serving with torchair graph mode and eager mode.

- vLLM version: v0.10.2
- vLLM main:
https://github.com/vllm-project/vllm/commit/759ef49b15149daaa0b2ba8900c1983e7e5e4514

---------

Signed-off-by: linfeng-yuan <1102311262@qq.com>
Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
Co-authored-by: yiz-liu <136800916+yiz-liu@users.noreply.github.com>
Co-authored-by: Yizhou Liu <liu_yizhou@outlook.com>
2025-09-16 14:13:07 +08:00
weichenandweijinqian0 18ca7861f6 [Main] [Refactor] Enable MoECommMethod in Eager Mode (#2791)
### What this PR does / why we need it?
1. Replace prepare/finalize operation in fused_moe.py by
moe_comm_method.prepare()/finalize()
2. Replace unified_fused_experts by moe_comm_method.fused_experts() in
fused_moe.py/w8a8_dynamic.py/w4a8_dynamic.py
3. Add calling _select_moe_comm_method in spec-decode proposers.
4. Currently, w4a8_dynamic does not support gatherep, use all2allv
instead.
5. Remove redundant code.
### Does this PR introduce _any_ user-facing change?
AllgatherEP switch is disabled in aclgraph/eager mode, just follow the
rules in modelrunner_v1._select_moe_comm_method()
### How was this patch tested?
e2e & ut


- vLLM version: v0.10.2
- vLLM main:
https://github.com/vllm-project/vllm/commit/7f6f2c1182b4f6e23d9d10715e25f60fbfd8e6ac

Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
Co-authored-by: weijinqian0 <12153182+weijinqian0@users.noreply.github.com>
2025-09-16 11:06:00 +08:00
Jiawei Li e57cca971c Fix the bugs about operator registration by PyTorch Dispatcher (#2786)
**Background:**

There are two principles about operator registration in PyTorch
- The same namespace can be only registered once by `TORCH_LIBRARY`
- The operator signatures can be only registered once by `def`

Considering that all custom operators defined in the current repo are
only used by Ascend, instead of defining a common operator schema by
vLLM, all accelerators then follow this operator schema and complete the
implementation based on their respective hardware, which is conducive to
functional abstraction.

Therefore, we can rename the operator registration namespace to an
Ascend-specific namespace(**_C_ascend**).

Related ISSUE: https://github.com/vllm-project/vllm-ascend/issues/2742


- vLLM version: main
- vLLM main:
https://github.com/vllm-project/vllm/commit/f592b3174b39a7aeac52432d66d76e89ff0a80b4

Signed-off-by: FFFrog <ljw1101.vip@gmail.com>
2025-09-13 11:58:52 +08:00
Yikun Jiang 756b8a1946 Revert "[Feat] Unquantized linear nz support (#2619)" (#2896)
### What this PR does / why we need it?
This reverts commit 7b2ecc1e9a.

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?
CI passed

- vLLM version: main
- vLLM main:
https://github.com/vllm-project/vllm/commit/64d90c3e4fe2a0e4395b8c94344dcdf78fa4cd22

Closes: https://github.com/vllm-project/vllm-ascend/issues/2890
Closes: https://github.com/vllm-project/vllm-ascend/issues/2887
Closes: https://github.com/vllm-project/vllm-ascend/issues/2885

Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
2025-09-12 20:51:12 +08:00
wuweiqiang24 9615dea3a7 Refactor tensor_parallel and comm_utils (#2814)
### What this PR does / why we need it?
1. Move ops/comm_utils to ops/moe/comm_utils
2. Move distributed/tensor_parallel/gather_from_sequence_parallel_region
to ops/moe/comm_utils
3. Delete distributed/tensor_parallel

### Does this PR introduce _any_ user-facing change?
no

### How was this patch tested?
e2e & ut

- vLLM version: main
- vLLM main:
https://github.com/vllm-project/vllm/commit/a1213fae5f8fe624c4b954768d23a86e384abdb1

---------

Signed-off-by: wuweiqiang24 <1005334931@qq.com>
Signed-off-by: wuweiqiang24 <wuweiqiang11@huawei.com>
2025-09-11 21:26:36 +08:00
rjg-lyhandShuming19 0005479b9c [main] mlp weight prefetch in Qwen Dense Models (#2816)
### What this PR does / why we need it?
This PR prefetchs the weight of mlp layers in Qwen Dense Models to
optimize the performance in Decode phase mainly.

### Does this PR introduce _any_ user-facing change?
 No.

### How was this patch tested?
CI passed with new added/existing test.

- vLLM version: main
- vLLM main:
https://github.com/vllm-project/vllm/commit/a1213fae5f8fe624c4b954768d23a86e384abdb1

Signed-off-by: rjg-lyh <1318825571@qq.com>
Co-authored-by: Shuming19 <313093131@qq.com>
2025-09-11 21:20:09 +08:00
无脸男 c3c2221503 [Feat]support dynamic quantization in allgather (#2841)
### What this PR does / why we need it?
[Feat]support dynamic quantization in allgather
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: main
- vLLM main:
https://github.com/vllm-project/vllm/commit/5931b7e5d9acd4fd9eb42d56086c379fa2e2014e

Signed-off-by: withHades <244036962@qq.com>
Signed-off-by: WithHades <244036962@qq.com>
2025-09-11 18:47:20 +08:00
anon189Ty 7b2ecc1e9a [Feat] Unquantized linear nz support (#2619)
### What this PR does / why we need it?
Currently, when executing to the Linear layer of the model in
vLLM-Ascend, the weights input format is ND in unquantized case and
skipped ascend case, which is slower than FRACTAL_NZ.
This PR supplements the execution logic for Linear layer. When
VLLM_ASCEND_ENABLE_MLP_OPTIMIZE=1 and CANN version is 8.3, the weights
of the Linear layer will be converted to FRACTAL_NZ, in both unquantized
case and skipped ascend case.

- vLLM version: main
- vLLM main:
https://github.com/vllm-project/vllm/commit/267c80d31f6b77092a5d5903da64556ac15c4d4d

Signed-off-by: anon189Ty <Stari_Falcon@outlook.com>
2025-09-11 11:40:00 +08:00
sherieandwangxiaoxin-sherie 93e28e6862 add weight transpose check. (#2756)
### What this PR does / why we need it?
In reinforcement learning scenarios, weight updates are required, but
the current inference applies a transpose operation to the weights,
altering their shape. This causes a shape mismatch with the training
weights, triggering an error during weight updates.

### Does this PR introduce _any_ user-facing change?

### How was this patch tested?


- vLLM version: v0.10.1.1
- vLLM main:
https://github.com/vllm-project/vllm/commit/6fb27881634d89c2e70e9e5fbad1b918c0d916cf

Signed-off-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
Co-authored-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
2025-09-09 20:33:43 +08:00
7a205dbaa8 [main] Optimize rope in Qwen Models (#2571)
### What this PR does / why we need it?
Optimize rope by caching sin and cos at the first layer in Qwen Models.

### Does this PR introduce _any_ user-facing change?
No.

### How was this patch tested?
CI passed with new added/existing test.


- vLLM version: v0.10.1.1
- vLLM main:
https://github.com/vllm-project/vllm/commit/562663a044acbff0b8df11e07a4929b18d71172f

---------

Signed-off-by: MengqingCao <cmq0113@163.com>
Signed-off-by: ZYang6263 <zy626375@gmail.com>
Signed-off-by: rjg-lyh <1318825571@qq.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>
Co-authored-by: ZYang6263 <51255902183@stu.ecnu.edu.cn>
Co-authored-by: ZYang6263 <zy626375@gmail.com>
2025-09-09 14:28:14 +08:00
rjg-lyhand1024daniel 1bbb20ea13 [main] flashcomm_v1 optim in Qwen Dense Models (#2802)
### What this PR does / why we need it?
Flashcomm_v1 optim in Qwen Dense Models.

### Does this PR introduce _any_ user-facing change?
No.

### How was this patch tested?
CI passed with new added/existing test.

- vLLM version: v0.10.1.1
- vLLM main:
https://github.com/vllm-project/vllm/commit/5e537f45b453096c489d06f0c47776f9436ef99b

Co-authored-by: 1024daniel <xxltju324@gmail.com>
2025-09-08 22:52:24 +08:00
zzzzwwjj 4df8df5b94 [bugfix] fix deepseek rope sincoscache re-generation (#2744)
### What this PR does / why we need it?
The current implementation will result in duplicate generation of
`sin_cos_cache` in rope when `kv_seqlen` > 4k, because the
initialization length of the `sin_cos_cache` is only 4k.

### Does this PR introduce _any_ user-facing change?
No.

### How was this patch tested?
After this PR merged, sin_cos_cache will not increase in forward func,
so `test_native_rope_deepseek_forward_cache_handling` is not necessary.

- vLLM version: v0.10.1.1
- vLLM main:
https://github.com/vllm-project/vllm/commit/60f0843ef8fb4b0c4e6788acc042873a0a2ea2a1

Signed-off-by: zzzzwwjj <1183291235@qq.com>
2025-09-08 22:03:34 +08:00
weichenandweijinqian0 a041d4f328 [main] [refactor] refactor common_fused_moe.py (#2706)
### What this PR does / why we need it?
1. Move prepare/finalize operation from moe_comm_method to
/ops/moe/fused_moe_prepare_and_finalize
2. Adapt to token_dispatcher in moe_comm_method
3. Move
moe_comm_method/experts_selector/token_dispatcher/fused_moe_prepare_and_finalize
to /ops/moe
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
e2e & ut

- vLLM version: v0.10.1.1
- vLLM main:
https://github.com/vllm-project/vllm/commit/f4962a6d55a340ebb569d377c842deff7611d8f7

Signed-off-by: weichen <calvin_zhu0210@outlook.com>
Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
Co-authored-by: weijinqian0 <12153182+weijinqian0@users.noreply.github.com>
2025-09-08 20:09:50 +08:00
sherieandwangxiaoxin-sherie 2693196ef8 add gatherep select. (#2740)
### What this PR does / why we need it?
add gatherep select.

- vLLM version: v0.10.1.1
- vLLM main:
https://github.com/vllm-project/vllm/commit/e599e2c65ee32abcc986733ab0a55becea158bb4

Signed-off-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
Co-authored-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
2025-09-08 09:15:50 +08:00
lidenghui1110andzzh 5a7181569c [feat]: oproj tensor parallelism in pure DP and graph-mode scenarios. (#2167)
### What this PR does / why we need it?
This PR introduces Oproj matrix tensor model parallel to achieve
decreasing of memory consumption. It only support graph mode in pure DP
scenario.

In deepseek r1 w8a8 PD disagregated Decode instance, using pure DP, with
oproj_tensor_parallel_size = 8, we have 1 ms TPOT increasing, saved 5.8
GB NPU memory per RANK. We got best performance when
oproj_tensor_parallel_size=4 without TPOT increasing.

performance data:
<img width="1442" height="442" alt="image"
src="https://github.com/user-attachments/assets/83270fc5-868a-4387-b0a9-fac29b4a376d"
/>

### Does this PR introduce _any_ user-facing change?
This PR introduces one new config in `additional_config`.
| Name | Effect | Required | Type | Constraints |
| :---------------------------- |
:--------------------------------------- | :------- | :--- |
:----------------- |
| oproj_tensor_parallel_size | Split the o_proj matrix along the row
dimension (head num * head dim) into oproj_tensor_parallel_size pieces.
| No | int | default value is None, once this value is set, the feature
will be enabled, head num * head dim must be divisible by this value. |

example

`--additional_config={"oproj_tensor_parallel_size": 8}`

### How was this patch tested?


- vLLM version: v0.10.1.1
- vLLM main:
https://github.com/vllm-project/vllm/commit/eddaafc1c77b0690194cbd1b73747d572793838c

---------

Signed-off-by: zzhx1 <zzh_201018@outlook.com>
Co-authored-by: zzh <zzh_201018@outlook.com>
2025-09-07 10:31:32 +08:00
henryxuxu0716and刘哲续 51a2aec115 Delete redundant codes related to communication (#2717)
### What this PR does / why we need it?
Delete redundant codes related to communication

### Does this PR introduce _any_ user-facing change?
not involve

### How was this patch tested?
not involve

- vLLM version: v0.10.1.1
- vLLM main:
https://github.com/vllm-project/vllm/commit/6c7af8110a2c383f18a9523bc26c26d3f599ff2e

---------

Signed-off-by: 刘哲续 <liuzhexu1@huawei.com>
Co-authored-by: 刘哲续 <liuzhexu1@huawei.com>
2025-09-05 09:39:39 +08:00
sherieandwangxiaoxin-sherie f86596a66c allgather use fusedop. (#2689)
### What this PR does / why we need it?
Use 'npu_moe_init_routing_v2' &'npu_moe_token_unpermute' repalce
'npu_moe_init_routing' &‘npu_moe_compute_expert_tokens’&
'npu_moe_finalize_routing' to optimize performance
### Does this PR introduce _any_ user-facing change?
| branch| tps| TTFT |TPOT |
| --- | --- | --- |--- |
|main  |733.98  | 280.05 |34.30 |
|main+fusedop  | 740.33 | 273.34 |33.99 |
### How was this patch tested?


- vLLM version: v0.10.1.1
- vLLM main:
https://github.com/vllm-project/vllm/commit/6997a25ac65ed6cc3c2be6d09ca45f633a345f63

Signed-off-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
Co-authored-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
2025-09-04 11:56:29 +08:00
Ruri aff5189c87 [main] Fuse GroupedMatmul, Swiglu and DynamicQuant in W8A8_DYNAMIC quantized MoE layers (#2275)
### What this PR does / why we need it?

Fuse `GroupedMatmul`, `Swiglu` and `DynamicQuant` into one fusion
operation `GroupedMatmulSwigluQuant`.

1. extract common functions in `w4a8_dynamic.py` and `w8a8_dynamic.py`
2. if in supported occasion, use fusion operation
`npu_grouped_matmul_swiglu_quant`

### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

Tested on W8A8 quantized Qwen3-235B-A22B model with `bs=16`

1. `tp=8`, `dp=1`, `moe_tp=8`, `moe_ep=1`, TPOP increased 21.54%, Output
Token Throughput increased 27.35%
<img width="3443" height="211" alt="image"
src="https://github.com/user-attachments/assets/a1a9c14d-2310-41be-9a03-36125dabae6e"
/>

3. `tp=8`, `dp=1`, `moe_tp=1`, `moe_ep=8`, TPOP increased 17.38%, Output
Token Throughput increased 6.86%
<img width="3443" height="211" alt="image"
src="https://github.com/user-attachments/assets/1ce92e92-720d-40c0-8b4d-c493e5cb10a6"
/>


- vLLM version: v0.10.1.1
- vLLM main:
https://github.com/vllm-project/vllm/commit/6997a25ac65ed6cc3c2be6d09ca45f633a345f63

---------

Signed-off-by: Ruri <33858552+zhoux77899@users.noreply.github.com>
Signed-off-by: zhoux77899 <zhouxiang100@huawei.com>
2025-09-04 11:37:32 +08:00
wangxiyuan c1e607b7b7 [Misc] Clean up uesless code in rotary_embedding (#2663)
Clean up useless code which is only used for torchair in rotary_embedding

- vLLM version: v0.10.1.1
- vLLM main:
https://github.com/vllm-project/vllm/commit/a344a5aa0a58cc1758d9721e848ce1f5ca4b6c7f

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
2025-09-02 17:25:33 +08:00
Wang Yixuan ad13964c71 [6/N][refactor]delete torchair in rotary ops (#2581)
### What this PR does / why we need it?
After moved torchair related rope ops into torchair_ops, split the
torchair from the origin rope ops to make the code clean.

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?
vLLM version: main
vLLM main:
https://github.com/vllm-project/vllm/commit/ab9f2cfd1942f7ddfee658ce86ea96b4789862af


- vLLM version: v0.10.1.1
- vLLM main:
https://github.com/vllm-project/vllm/commit/81eea3d348c26fb1e6ff0185ad109aedd60a28a2

Signed-off-by: hust17yixuan <303660421@qq.com>
2025-09-01 09:10:15 +08:00
weichenandweijinqian0 3a5fc5ee01 [Refactor][MoE] remove redundant code after refactoring fused_moe (#2612)
### What this PR does / why we need it?
There are a lot of redundant codes related to moe here, and the
structure is not very clear.
We did the following things:

we have placed the relatively independent code related to apply_mlp into
a separate file;
removed the environment variables of alltoall_buffer and alltoall_seq.
Remove the code related to alltoall_buffer and alltoall_seq, and retain
the sole TokenDispatcher inheritance class.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
e2e&ut

- vLLM version: v0.10.1.1
- vLLM main:
https://github.com/vllm-project/vllm/commit/4071c76cf3cff46e14630f1e66cbf006b6eb51d3

---------

Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Co-authored-by: weijinqian0 <12153182+weijinqian0@users.noreply.github.com>
2025-08-30 22:28:50 +08:00
weichen 52aff9e229 [main] [bugfix] Fix misjudging quantized/unquantized scenarios (#2627)
### What this PR does / why we need it?
In a mixed-precision scenario, quant_config is not None, but MoE needs
to perform unquantized computation; however, quantized computation is
currently being used. Therefore, we put the with_quant logic into
forward, avoid misjudging in mix-precision scenarios.
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
e2e & ut

- vLLM version: v0.10.1.1
- vLLM main:
https://github.com/vllm-project/vllm/commit/98ac0cb32d9462e50bd998f9f2eb6e4c09232c95

Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
2025-08-29 16:20:22 +08:00
lidenghui1110andzhangzihang 600b08f754 [Feat]: Add custom lmhead tensor model parallel (#2309)
### What this PR does / why we need it?
This PR introduces LMhead tensor model parallel to achieve decreasing of
memory consumption, and TPOT performance improvement. It support both
eager mode and graph mode.

In deepseek r1 w8a8 PD disagregated Decode instance, using pure DP, with
lmhead_tensor_parallel_size = 8, we have 1 ms TPOT optimization, saved
1.48 GB NPU memory per RANK.

performance data:
<img width="1444" height="438" alt="image"
src="https://github.com/user-attachments/assets/3c5ef0d3-a7c7-46fd-9797-4de728eb0cb0"
/>

### Does this PR introduce _any_ user-facing change?
This PR introduces one new config in `additional_config`.
| Name | Effect | Required | Type | Constraints |
| :---------------------------- |
:--------------------------------------- | :------- | :--- |
:----------------- |
| lmhead_tensor_parallel_size | Split the lm_head matrix along the
column dimension (vocab_size) into lmhead_tensor_parallel_size pieces |
No | int | default value is None, once this value is set, the feature
will be enabled, vocab_size must be divisible by this value. |

example

`--additional_config={"lmhead_tensor_parallel_size": 8}`

### How was this patch tested?


- vLLM version: v0.10.1.1
- vLLM main:
https://github.com/vllm-project/vllm/commit/de533ab2a14192e461900a4950e2b426d99a6862

---------

Signed-off-by: zzhx1 <zzh_201018@outlook.com>
Co-authored-by: zhangzihang <zzh_201018@outlook.com>
2025-08-29 11:41:21 +08:00
320edde2df [main] [refactor] refactor fused_moe.py to enable token_dispatchers (#2570)
### What this PR does / why we need it?
Enable token_dispatcher to replace fused_experts_with_xxx in eager mode
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
e2e & ut


- vLLM version: v0.10.1.1
- vLLM main:
https://github.com/vllm-project/vllm/commit/704432af3c129b7a57fca9b059eefe214159f836

Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
Co-authored-by: sherie <963372609@qq.com>
Co-authored-by: weijinqian0 <12153182+weijinqian0@users.noreply.github.com>
Co-authored-by: shiyuan680 <72335504+shiyuan680@users.noreply.github.com>
2025-08-28 10:13:35 +08:00
Icey c578f817ca [CustomOp] Register VocabParallelEmbedding instead of overwrite forward (#2515)
### What this PR does / why we need it?
Register VocabParallelEmbedding instead of overwrite forward

### Does this PR introduce _any_ user-facing change?
N/A

### How was this patch tested?
CI passed with new added/existing test.

- vLLM version: v0.10.1.1
- vLLM main:
https://github.com/vllm-project/vllm/commit/644d57d53191b94d9e50a4765891c498790d924b

---------

Signed-off-by: Icey <1790571317@qq.com>
2025-08-28 08:57:34 +08:00
huangxialu 6881c19458 [main] convert the format of gmm to nz (#2474)
### What this PR does / why we need it?
convert the format of gmm to nz

### Does this PR introduce _any_ user-facing change?
not involved

### How was this patch tested?
ut: test_fused_ops.py and e2e: test_fused_moe.py

**performance**:
(qwen3 30B, 2k->20k)

base:
Total Token throughput (tok/s):          719.93

gmm nz:
Total Token throughput (tok/s):          728.52


- vLLM version: v0.10.1.1
- vLLM main:
https://github.com/vllm-project/vllm/commit/bfc1edc9f5bde581e0eec5c830a5a4a7b710fe6a

Signed-off-by: huangxialu <huangxialu1@huawei.com>
2025-08-27 11:25:02 +08:00
s30076806 6a4ec186e7 [Qwen-moe] Remove the minor operation arange (#2373)
### What this PR does / why we need it?
Integrate the arange operator to reduce the time spent and improve
performance

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?

- vLLM version: v0.10.1.1
- vLLM main:
https://github.com/vllm-project/vllm/commit/56dcf4e7e965e34043acf20ca4e4aceda21d41ec

---------

Signed-off-by: s30076806 <songjiayang2@h-partners.com>
2025-08-27 09:13:31 +08:00
Icey f796e6280b [CustomOp] Register RotaryEmbedding instead of overwrite forward (#2385)
### What this PR does / why we need it?
Register RotaryEmbedding instead of overwrite forward

### Does this PR introduce _any_ user-facing change?
N/A

### How was this patch tested?
CI passed with new added/existing test.

- vLLM version: v0.10.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/808d2e9aa0f302bf9667b09b9dcf297f86927dac

---------

Signed-off-by: Icey <1790571317@qq.com>
Signed-off-by: wxsIcey <1790571317@qq.com>
2025-08-25 09:32:35 +08:00
weichen 950c4b219a [main] refactor alltoallv in fused_moe (#2487)
### What this PR does / why we need it?
Refactor all2all-related fused_experts (both quantized/unquantized) into
TokenDispatcherWithAll2AllV, including dispatch & combine calculation.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
E2E & UT
- vLLM version: v0.10.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/65197a5fb37ef4d8b93e0b99ecc8b902fe948e97

Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
2025-08-23 20:38:17 +08:00
sherieandwangxiaoxin-sherie 3fb80ee356 add mlp tp optimze (#2120)
### What this PR does / why we need it?
For dense models, by not applying tensor parallelism (TP) to the
attention module and applying TP to the MLP module, the allreduce
operations in the attention module can be eliminated, thereby reducing
computational overhead. However, this approach increases memory usage,
so the environment variable VLLM_ASCEND_ENABLE_MLP_OPTIMZE is used to
control this optimization.

- vLLM main:
https://github.com/vllm-project/vllm/commit/b17109beeafbf9577c319ab61530810943a7fc4b

Signed-off-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
Co-authored-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
2025-08-21 09:22:07 +08:00
sherieandwangxiaoxin-sherie 3f867ee708 refactor allgather/mc2-related fused_experts (#2369)
### What this PR does / why we need it?
refactor allgather/mc2-related fused_experts

- vLLM version: v0.10.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/de7b67a0232e35ae8e8ecd944aeddfc8cbc02631

Signed-off-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
Co-authored-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
2025-08-20 14:20:46 +08:00
1327f9be1c Fix some ci issue and refactor modelrunner (#2445)
### What this PR does / why we need it?
Fix some ci issue and refactor modelrunner

### Does this PR introduce _any_ user-facing change?
N/A

### How was this patch tested?
CI passed with existing test.

- vLLM version: v0.10.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/4d9c61993ac4209c97b3afef237b2387f2cd9b97

---------

Signed-off-by: wangli <wangli858794774@gmail.com>
Signed-off-by: MengqingCao <cmq0113@163.com>
Signed-off-by: weiguihua2 <weiguihua2@huawei.com>
Co-authored-by: wangli <wangli858794774@gmail.com>
Co-authored-by: weiguihua2 <weiguihua2@huawei.com>
2025-08-20 09:01:04 +08:00
Icey c721ae6042 [CustomOp] Register RMSNorm instead of overwrite forward_oot (#2284)
### What this PR does / why we need it?
Use function CustomOp.register_oot to achieve the customop registery
```
from vllm.model_executor.custom_op import CustomOp
CustomOp.register_oot(_decorated_op_cls=AscendRMSNorm, name="RMSNorm")
```

### Does this PR introduce _any_ user-facing change?
N/A

### How was this patch tested?
CI passed with new added/existing test.

- vLLM version: v0.10.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/afa5b7ca0b417abadfa85e32f28969b72e58a885

---------

Signed-off-by: Icey <1790571317@qq.com>
2025-08-14 17:18:30 +08:00
shiyuan680andyangcheng e14f2ef669 refactor select_experts of moe module (#2150)
### What this PR does / why we need it?
this pr refactor select_experts of moe module
i merge implementations of quantitative and non-quantitative method in a
new class
use such as vllm like ExpertsSelector.select_experts
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
test in qwen3-moe and all ut.

- vLLM version: v0.10.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/e18859298d109870b22cb5b8672d1078818e268d

Signed-off-by: yangcheng <yangcheng104@huawei.com>
Co-authored-by: yangcheng (AJ) <y00806874@china.huawei.com>
2025-08-14 11:50:53 +08:00
Mengqing Cao ad1083761f [CI][Quickfix] Fix AscendFusedMoE init error (#2268)
### What this PR does / why we need it?
Fix AscendFusedMoE init error. Use `super().__init__()` instead of
`super(FusedMoE, self).__init__()` to ensure the member variables in
base class could be called by the children class

### Does this PR introduce _any_ user-facing change?
N/A
### How was this patch tested?
CI passed with new existing test.


- vLLM version: v0.10.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/766bc8162cb37ad32605eee051d4f049ec325926

---------

Signed-off-by: MengqingCao <cmq0113@163.com>
2025-08-08 10:20:23 +08:00
huangxialu dceef080b1 [main] remove torch.cat and replace it by List[0] (#2153)
### What this PR does / why we need it?
torch_npu.npu_grouped_matmul:

https://www.hiascend.com/document/detail/zh/Pytorch/710/apiref/torchnpuCustomsapi/context/torch_npu-npu_grouped_matmul.md

According to the document, when `split_item` is 2 or 3,
`torch_npu.npu_grouped_matmul` will return a list which has one element.
Therefore, the `torch.cat` after `torch_npu.npu_grouped_matmul` is
unnecessary.

### Does this PR introduce _any_ user-facing change?
not involved

### How was this patch tested?
ut and e2e covered: `tests/ut/ops/test_fused_ops.py`,
`tests/e2e/singlecard/ops/test_fused_moe.py`

**performance**:
(qwen3 30B, 2k->20k)

base:
Total Token throughput (tok/s):          667.76 

remove cat:
Total Token throughput (tok/s):          680.82 


- vLLM version: v0.10.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/fa00c5d75bc63c87f5822f839db1342f19e4acc8

Signed-off-by: huangxialu <huangxialu1@huawei.com>
2025-08-07 17:20:19 +08:00
wangxiyuan 36e450eb0f [Misc] Nit fix for disaggregated_prefill and ascend_forward_context (#2097)
we recently added disaggregated_prefill and ascend_forward_context
feature by
https://github.com/vllm-project/vllm-ascend/commit/ba3dfbd59e43b9071895f483d12c034d8538ced0
and
https://github.com/vllm-project/vllm-ascend/commit/df0ec55162339c08b0bfcb79a2dcfac89f8c6e33.
This PR fix some nit introduced by them to make the code clear.
1. drop `current_platform` usage. It'll lead unknown circular import
error in some case
2. update `set_ascend_forward_context` function to make the logic clear.
for example, remove V0 support in this function.
3. Remove useless `self.local_rank_across_dp` in worker
4. Remove `soc_info.py` to use `get_ascend_soc_version` instead.
 

- vLLM version: v0.10.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/02f82fe4386b3e84eb0f06bfaf7744c5b4fdba4f

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
2025-08-05 08:39:02 +08:00
+1 6e00aed4d5 [main][Feature]Moe alltoallv communication optimization for unquantized RL training sence (#2088)
It comes from 0.9.1dev
[0.9.1][Feature]Moe alltoallv communication optimization for unquantized
RL training sence & alltoallv support dpo (#1547)

- vLLM version: v0.10.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/97608dc276c292d9217eb6d334d969c5e89913c6

---------

Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Signed-off-by: whx-sjtu <2952154980@qq.com>
Signed-off-by: curryliu <120010041@link.cuhk.edu.cn>
Signed-off-by: wangli <wangli858794774@gmail.com>
Signed-off-by: ChenTaoyu-SJTU <ctynb@qq.com>
Signed-off-by: taoxudonghaha <justsheldon@163.com>
Signed-off-by: shen-shanshan <467638484@qq.com>
Signed-off-by: Shanshan Shen <87969357+shen-shanshan@users.noreply.github.com>
Signed-off-by: leo-pony <nengjunma@outlook.com>
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Signed-off-by: MengqingCao <cmq0113@163.com>
Co-authored-by: weijinqian_v1 <weijinqian@huawei.com>
Co-authored-by: whx <56632993+whx-sjtu@users.noreply.github.com>
Co-authored-by: curryliu <99582471+Irving11-BKN@users.noreply.github.com>
Co-authored-by: Li Wang <wangli858794774@gmail.com>
Co-authored-by: TaoYu Chen <ctynb@qq.com>
Co-authored-by: taoxudonghaha <justsheldon@163.com>
Co-authored-by: Shanshan Shen <467638484@qq.com>
Co-authored-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>
2025-08-02 09:49:10 +08:00
huangxialu 9c9a7cd90b [main] adapt usage of npu_moe_gating_top_k_softmax and remove envs.SELECT_GATING_TOPK_SOTFMAX_EXPERTS (#2112)
backport of v0.9.1-dev:
https://github.com/vllm-project/vllm-ascend/pull/1902

origin main npu_moe_gating_top_k_softmax:
https://github.com/vllm-project/vllm-ascend/pull/1355

- vLLM version: v0.10.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/055bd3978ededea015fb8f0cb6aa3cc48d84cde8

Signed-off-by: huangxialu <huangxialu1@huawei.com>
2025-07-31 21:05:56 +08:00
YuanCheng-coderandchengyuan 34dd24adf2 add ut for vocab_parallel_embedding (#2067)
### What this PR does / why we need it?

test vllm_ascend/ops/vocab_parallel_embedding.py contains vocab parallel
embedding forward

CI passed with new added test.

vLLM version: v0.10.0
vLLM main:
https://github.com/vllm-project/vllm/commit/2cc571199b1446f376ee019fcafda19155fc6b71


- vLLM version: v0.10.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/05cbbe20c55d957f18c12f7eb11cf551504e657d

Signed-off-by: chengyuan <chengyuan27@huawei.com>
Co-authored-by: chengyuan <chengyuan27@huawei.com>
2025-07-30 14:35:45 +08:00