Currently, the vllm pull request
(https://github.com/vllm-project/vllm/pull/24252) is causing operator
fusion to fail. This issue was previously fixed by patching the backend.
The root cause has been identified, and the problem can be resolved with
this pull request.
- vLLM version: v0.13.0
- vLLM main:
2f4e6548ef
---------
Signed-off-by: wxsIcey <1790571317@qq.com>
### What this PR does / why we need it?
Import global var form vllm instead of overwirte it, so that we could
use the correct global variant value
- vLLM version: v0.13.0
- vLLM main:
5326c89803
---------
Signed-off-by: MengqingCao <cmq0113@163.com>
### What this PR does / why we need it?
Revert PR 5253 to fix the smoking problem
### Does this PR introduce _any_ user-facing change?
Does not.
### How was this patch tested?
It was tested in the failure case.
Signed-off-by: Rifa <865071616@qq.com>
Currently, the vllm pull request
(https://github.com/vllm-project/vllm/pull/24252) is causing operator
fusion to fail. This issue was previously fixed by patching the backend.
The root cause has been identified, and the problem can be resolved with
this pull request.
- vLLM version: release/v0.13.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: wxsIcey <1790571317@qq.com>
### What this PR does / why we need it?
Fix the bug in the PCP overlay feature
1、Fix the bug related to PCP and EPLB overlap by including PCP size in
the word_size calculation.
2、In the PCP pooling scenario, a prompt has been added for setting the
cp_kv_cache_interleave_size.
- vLLM version: v0.13.0
- vLLM main:
7157596103
Signed-off-by: weiguihua2 <weiguihua2@huawei.com>
### What this PR does / why we need it?
We should transfer the mm_embed to the dtype of input_embed before
performing the in-place assignment
- vLLM version: release/v0.13.0
- vLLM main:
ad32e3e19c
Signed-off-by: wangli <wangli858794774@gmail.com>
Currently, the vllm pr: https://github.com/vllm-project/vllm/pull/24252
is causing operator fusion to fail, which can be mitigated by patching
the backend. Once the problem is completely resolved, I will submit a
new pull request to remove the patch.
- vLLM version: release/v0.13.0
- vLLM main:
5fbfa8d9ef
---------
Signed-off-by: wxsIcey <1790571317@qq.com>
### What this PR does / why we need it?
Following https://github.com/vllm-project/vllm/pull/29873, register
`AscendApplyRotaryEmb` CustomOp and remove related patch.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
#### ✅ Test Qwen2.5-VL
Run:
```bash
vllm serve /root/.cache/modelscope/hub/models/Qwen/Qwen2.5-VL-7B-Instruct \
--max_model_len 16384
```
Output:
```
{"id":"chatcmpl-b02c1ff3415d2462","object":"chat.completion","created":1766129265,"model":"/root/.cache/modelscope/hub/models/Qwen/Qwen2.5-VL-7B-In struct","choices":[{"index":0,"message":{"role":"assistant","content":"The text in the illustration is \"TONGYI Qwen.\" The word \"TONGYI\" is writ ten in blue, and \"Qwen\" is written in gray. The text appears to be part of a logo or branding design.","refusal":null,"annotations":null,"audio": null,"function_call":null,"tool_calls":[],"reasoning":null,"reasoning_content":null},"logprobs":null,"finish_reason":"stop","stop_reason":null,"tok en_ids":null}],"service_tier":null,"system_fingerprint":null,"usage":{"prompt_tokens":78,"total_tokens":129,"completion_tokens":51,"prompt_tokens_d
```
#### ✅ Test Qwen3-VL
Run:
```bash
vllm serve /root/.cache/modelscope/hub/models/Qwen/Qwen3-VL-8B-Instruct \
--max_model_len 16384
```
Output:
```
{"id":"chatcmpl-a3a7de5a900a9321","object":"chat.completion","created":1766129586,"model":"/root/.cache/modelscope/hub/models/Qwen/Qwen3-VL-8B-Instruct","choices":[{"index":0,"message":{"role":"assistant","content":"The text in the illustration is **“TONGYI Qwen”**.\n\n### How it looks:\n- **“TONGYI”** is written in **uppercase letters** in a **bold, modern sans-serif font**, colored **blue**.\n- **“Qwen”** is written in **lowercase letters** in a **slightly thinner, elegant sans-serif font**, colored **dark gray**.\n- The two lines of text are stacked vertically, with “TONG","refusal":null,"annotations":null,"audio":null,"function_call":null,"tool_calls":[],"reasoning":null,"reasoning_content":null},"logprobs":null,"finish_reason":"length","stop_reason":null,"token_ids":null}],"service_tier":null,"system_fingerprint":null,"usage":{"prompt_tokens":112,"total_tokens":212,"completion_tokens":100,"prompt_tokens_details":null},"prompt_logprobs":null,"prompt_token_ids":null,"kv_transfer_params":null}
```
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: shen-shanshan <467638484@qq.com>
### Motivation.
**Limitations of the current vLLM v1 scheduling strategy**
vLLM v1 scheduling currently enables chunkedprefill by default, which
processes prefill and decode requests simultaneously in a single
scheduling session. This can impact the overall system throughput and
performance in some scenarios.
Balance scheduling addresses this issue by synchronizing the number of
running queues across all schedulers to delay the scheduling of new
requests, thereby improving the overall system's steady-state decoding
time. This achieves:
✅Adding `balance_gather` to the scheduler synchronizes the number of
requests in the running queues between DPs.
✅Balance scheduling improves the decode steady-state time, thereby
increasing the overall output throughput of the inference system.
### Proposed Change.
**1.Feature Overview**
In the vLLM scheduler, running requests (i.e., requests that are already
undergoing pre-filled computation) have the highest priority, followed
by waiting requests (i.e., requests that have not yet been computed).
As shown in the diagram above, when the entire inference system exits
from a steady state, the scheduler will schedule a batch of new requests
for prefill operations and then synchronize them among the dynamic
programming (DP) models. This can cause some DP models that are entirely
decoded to synchronize with the number of prefilled tokens. Frequent
prefill scheduling by certain DP models can lead to a deterioration in
the overall system output throughput.
Balance scheduling synchronizes the number of running queue requests
across different DPs, and only schedules new requests for prefilling
when at least every scheduler has fewer than max_nun_requst.
**2.Implementation Design**
**3.Experiment Results**
- Fixed-length input scenario: In the performance test scenario with
3.5K fixed-length input and 1.5K fixed-length output, the throughput
performance was improved by approximately **18%** after adding balance
scheduling.
| Method | Model | Input Len | Request Count | Output Len | BatchSize |
Average TTFT | Average TPOT | e2e duration | Input Token Throughput |
Output Token Throughput | Request Throughput
| ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- |
---- | ---- |
| Baseline | DeepSeekV3.1 | 3500 | 512 | 1500 | 128 | 6600 | 86.85 |
591.9s | 3030.5 | 1297.3 | 0.86 |
| Balance scheduling | DeepSeekV3.1 | 3500 | 512 | 1500 | 128 | 7012 |
70.63 | 501.7s | 3575.7 | 1530.7 | 1.02 |
**4.Demo PR**
[#29721 ](https://github.com/vllm-project/vllm/pull/29721)
---------
Signed-off-by: GDzhu01 <809721801@qq.com>
### What this PR does / why we need it?
Following https://github.com/vllm-project/vllm/pull/30125, register
`AscendMMEncoderAttention` CustomOp and remove related patch.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
✅ Run Qwen2.5-VL:
```bash
vllm serve /root/.cache/modelscope/hub/models/Qwen/Qwen2.5-VL-7B-Instruct \
--max_model_len 16384
```
Output:
```
{"id":"chatcmpl-b4e3053f30ab2442","object":"chat.completion","created":1764922950,"model":"/root/.cache/modelscope/hub/models/Qwen/Qwen2.5-VL-7B-Instruct","choices":[{"index":0,"message":{"role":"assistant","content":"The text in the image is \"TONGYI Qwen.\" The word \"TONGYI\" is written in blue, and \"Qwen\" is written in gray. The font appears to be modern and clean, with \"TONGYI\" being slightly larger than \"Qwen.\" The design includes a geometric, abstract shape on the left side of the logo, which complements the text.","refusal":null,"annotations":null,"audio":null,"function_call":null,"tool_calls":[],"reasoning":null,"reasoning_content":null},"logprobs":null,"finish_reason":"stop","stop_reason":null,"token_ids":null}],"service_tier":null,"system_fingerprint":null,"usage":{"prompt_tokens":78,"total_tokens":162,"completion_tokens":84,"prompt_tokens_details":null},"prompt_logprobs":null,"prompt_token_ids":null,"kv_transfer_params":null}
```
✅ Run Qwen3-VL:
```bash
vllm serve /root/.cache/modelscope/hub/models/Qwen/Qwen3-VL-8B-Instruct \
--max_model_len 16384
```
Output:
```
{"id":"chatcmpl-97571fbda8267bd1","object":"chat.completion","created":1764923306,"model":"/root/.cache/modelscope/hub/models/Qwen/Qwen3-VL-8B-Instruct","choices":[{"index":0,"message":{"role":"assistant","content":"The text in the illustration is **“TONGYI Qwen”**.\n\n### How it looks:\n- **“TONGYI”** is written in **uppercase letters** in a **bold, modern sans-serif font**, colored **blue**.\n- **“Qwen”** is written in **lowercase letters** in a **slightly thinner, elegant sans-serif font**, colored **dark gray**.\n- The two lines of text are stacked vertically, with “TONG","refusal":null,"annotations":null,"audio":null,"function_call":null,"tool_calls":[],"reasoning":null,"reasoning_content":null},"logprobs":null,"finish_reason":"length","stop_reason":null,"token_ids":null}],"service_tier":null,"system_fingerprint":null,"usage":{"prompt_tokens":112,"total_tokens":212,"completion_tokens":100,"prompt_tokens_details":null},"prompt_logprobs":null,"prompt_token_ids":null,"kv_transfer_params":null}
```
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: shen-shanshan <467638484@qq.com>
Co-authored-by: Yikun Jiang <yikunkero@gmail.com>
### What this PR does / why we need it?
This commit introduces a Triton-based fused GDN gating kernel for Ascend
NPU, aimed at improving performance in the Gated Delta Net workflow.
### Does this PR introduce _any_ user-facing change?
It only adds and refactors internal Triton kernels and wrappers for
Ascend. These are backend implementation details. There are no new APIs,
flags, CLI options, or behavior changes visible to end users.
### How was this patch tested?
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: Ascendyh <hw7osiris@outlook.com>
We decided to release v0.13.0 soon. So no need to support 0.12.0 now.
Let's drop it.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
qwen3_next add fused_sigmoid_gating_delta_rule_update op which fused
fused_gdn_gating+fused_recurrent_gated_delta_rule
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
Co-authored-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
### What this PR does / why we need it?
add triton ops fused_qkvzba_split_reshape_cat for qwen3_next
GatedDeltaNet
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
UT
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: ZT-AIA <1028681969@qq.com>
Signed-off-by: ZT-AIA <63220130+ZT-AIA@users.noreply.github.com>
### What this PR does / why we need it?
Related to #4084. Before we add the patches temporarily for making
`set_forward_context` patched by `set_ascend_forward_context` in the
function `_process_image_input` and `_process_video_input` of
`Qwen2.5-VL` and `Qwen2.5-Omni` models. After removing these patches, I
met the `AttributeError` for `ForwardContext` missing
`prefetch_mlp_enabled`. So we need to add the defensive check for
`prefetch_mlp_enabled`.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
```
vllm serve Qwen/Qwen2.5-VL-7B-Instruct \
--max-model-len 30000 \
--max-num-batched-tokens 50000 \
--max-num-seqs 30 \
--no-enable-prefix-caching \
--trust-remote-code \
--dtype bfloat16
```
```
{"id":"chatcmpl-b66d8acb76905c49","object":"chat.completion","created":1765796863,"model":"/root/.cache/modelscope/hub/models/Qwen/Qwen2.5-VL-7B-Instruct","choices":[{"index":0,"message":{"role":"assistant","content":"The text in the illustration reads \"TONGYI Qwen.\"","refusal":null,"annotations":null,"audio":null,"function_call":null,"tool_calls":[],"reasoning":null,"reasoning_content":null},"logprobs":null,"finish_reason":"stop","stop_reason":null,"token_ids":null}],"service_tier":null,"system_fingerprint":null,"usage":{"prompt_tokens":73,"total_tokens":88,"completion_tokens":15,"prompt_tokens_details":null},"prompt_logprobs":null,"prompt_token_ids":null,"kv_transfer_params":null}
```
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
Currently, we are using `AscendRejctionSampler` that extends from
`RejctionSampler` in spec decoding. `AscendRejctionSampler` override
`forward` of `RejctionSampler`, only aming to replace `rejection_sample`
func. This
causes a lot of code of `RejctionSampler` cannot be reused, for example:
- https://github.com/vllm-project/vllm/pull/19482
- https://github.com/vllm-project/vllm/pull/26060
- https://github.com/vllm-project/vllm/pull/29223
#### Proposed Change:
- Delete `AscendRejctionSampler` and use `RejctionSampler` directly in
model runner.
- Patch `RejctionSampler.expand_batch_to_tokens` and
`RejctionSampler.rejection_sample`, maybe a better way is to make them
as custom ops.
- Modify `NPUModelRunner` following
https://github.com/vllm-project/vllm/pull/26060
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
- [x] test logits processor for spec decoding
- [x] test logprobs for spec decoding
- [x] test logprobs for spec decoding + async shcheduling (test with
https://github.com/vllm-project/vllm-ascend/pull/4893/)
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: realliujiaxu <realliujiaxu@163.com>
### What this PR does / why we need it?
Support triton causal_conv1d_fn ops.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
CI passed with new added/existing test.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: QilaiZhang <245706640@qq.com>
Update patch doc. After this PR is merged, all the new patch PR should
update this doc as well.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
Support pooling models (like `bge-reranker-v2-m3`) in vllm-ascend, this
pr covered the three model types of embed (cls_token, mean_token,
lasttoken).
After this
[commit](17373dcd93),
vllm has provided support for adapting pooling models on the v1 engine.
This PR includes corresponding adaptations on the vllm-ascend side.
Fixes#1960
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: lianyibo <lianyibo1@kunlunit.com>
Signed-off-by: MengqingCao <cmq0113@163.com>
Co-authored-by: MengqingCao <cmq0113@163.com>
### What this PR does / why we need it?
Add Qwen3Next support in main
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2
---------
Signed-off-by: SunnyLee219 <3294305115@qq.com>
### What this PR does / why we need it?
This PR integrate suffix decoding (https://arxiv.org/abs/2411.04975)
from vllm (https://github.com/vllm-project/vllm/pull/25784)
#
Suffix Decoding is a dynamic n-gram matching method that:
1. Uses suffix trees to generate speculative tokens quickly using branch
frequency counts.
2. Can keep a history of prior model responses, which tends to work very
well with repetitive agentic use cases.
3. Can be dynamically updated with newly generated tokens, and FIFO
eviction of older requests.
#
### Does this PR introduce _any_ user-facing change?
This feature should be implemented as opt-in and remain seamless for
users who do not require suffix speculative decoding.
For users who wish to enable it, they must first install
arctic-inference:
`pip install arctic-inference
`
After installation, the suffix speculative decoding feature can be
enabled using the following speculative config:
`--speculative_config '{"method": "suffix", "num_speculative_tokens":
5}'
`
### How was this patch tested?
This PR is currently being tested on vLLM
main:83f478bb19
with PR https://github.com/vllm-project/vllm/pull/25784
In our previous testing, suffix decoding achieved a 13%-30% throughput
improvement over n-gram on the sonnet dataset, tested on vllm-ascend
v0.9.1 with concurrency ranging from 2 to 40.
- vLLM version: v0.11.2
---------
Signed-off-by: fluctlux <38945811+fluctlux@users.noreply.github.com>
Qwen2.5_Omni vision tower use AscendRMSNorm, which conatins a property
function. It would be override by set_forward_context(), patch
Qwen2_5OmniThinkerForConditionalGeneration func with customized
_process_image_input() and _process_video_input() to fix it.
### What this PR does / why we need it?
Fix Qwen2.5_Omni model infer image/video issue
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2
Signed-off-by: Ting FU <futing10@huawei.com>
### What this PR does / why we need it?
qwen3-next suppot triton chunk_gated_delta_rule ops
### co-owners
@OsirisDuan
- vLLM version: v0.11.2
Signed-off-by: shiyuan680 <917935075@qq.com>
### What this PR does / why we need it?
- [x] Patch `Qwen2_5_VisionAttention` with
`AscendQwen2_5_VisionAttention`.
- [x] Replace `AscendQwen2_5_VisionTransformer` with
`Qwen2_5_VisionTransformer` in vllm.
- [x] Move padding logic (q/k/v and cos/sin) before FA to `forward()` of
`Qwen2_5_VisionAttention`.
- [x] Covert `cu_seqlens` in `Qwen2_5_VisionAttention` from cumulative
form to intervals and move it to cpu (compatible for npu FA).
- [x] Remove Qwen2.5-VL modeling files.
- [x] Remove Qwen2.5-VL (without padding) modeling files.
- [x] Remove related UT.
- [x] Make `set_forward_context` pluggable when getting MM embedding.
Find more details at https://github.com/vllm-project/vllm/pull/29388.
- [x] Simplify padding logic for FA.
- [x] Add patch for https://github.com/vllm-project/vllm/pull/28798.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
- [x] Functional test (eager mode)
- [x] Functional test (graph mode)
- [x] Benchmark
- vLLM version: v0.11.2
---------
Signed-off-by: shen-shanshan <467638484@qq.com>
### What this PR does / why we need it?
Currently, there are two paths to judge the chip type in code,
`get_ascend_soc_version` use `get_soc_version` api in torch_npu, and
`is_310p` `use _build_info.__soc_version__`, which generate when
install. We need to unify the two paths.
We need to unify these codes based on the following points:
1. We need to ensure consistency in chip type judgment between compiling
and running states;
2. In compiling state, we need chip type to complete op's compilation,
but in running state, we only need device
type(910B/910_93/310P/910_95/etc) to make code branch judgement;
3. In compiling state, torch_npu may not have been installed yet, so we
can't use torch_npu's api.
Based on the above points, we have made the following changes:
1. When user set env `SOC_VERSION`, use it; when not set, query
soc_version by `npu-smi`;
2. generate device_type based on soc_version when compiling, and write
`__device_type__` instead of `__soc_version__` in `_build_info.py`;
3. In running state, use `__device_type__` to judge code branch.
### Does this PR introduce _any_ user-facing change?
When not set env `SOC_VERSION`, it will not be `ASCEND910B1` by default,
we will query soc_version by `npu-smi`. And env `SOC_VERSION` must be in
the list `soc_to_device` in `setup.py`.
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
Signed-off-by: zzzzwwjj <1183291235@qq.com>
### What this PR does / why we need it?
mkdir triton package and move triton files
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
Signed-off-by: shiyuan680 <917935075@qq.com>
Torch-npu 2.7.1 has fixed the device check bug. This patch can be
removed now.
- vLLM main:
2918c1b49c
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
Fix a bug caused by this pr:
https://github.com/vllm-project/vllm-ascend/pull/4223
The bug makes
vllm-ascend/vllm_ascend/patch/platform/patch_multiproc_executor.py patch
in a wrong way
### How was this patch tested?
Tested in a single node. When the environment DYNAMIC_EPLB is set to
true, the patch works correctly. When it's set to false, the patch do
not patch
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
Signed-off-by: 白永斌 <baiyongbin3@h-partners.com>
Co-authored-by: 白永斌 <baiyongbin3@h-partners.com>
There is a lot hack code for v0.11.0, which makes the code hard to
upgrade to newer vLLM version. Since v0.11.0 will release soon. Let's
drop v0.11.0 support first. Then we'll upgrade to v0.11.2 soon.
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
Currently, the MTP model still runs in eager in full graph mode. This PR
adapts the MTP with the full graph capture and execution. When the graph
mode is set to "FULL_DECODE_ONLY", the MTP will run in full-graph to
improve the performance.
The change in both disable_padded_drafter_batch is True and False case
include:
1. Add _mtp_graph_params in acl_graph.py to isolate the data of main
model and the data of MTP.
2. Padding some metadata in mla_v1.py when in fullgraph mode.
3. Fixed the essential data address that will be used in model.forward.
4. Adapted according to the aclgraph capture framwork:
1). Rebuild MTP model with ACLGraphWrapper.
2). Add common attn metadata when start capture in MTP dummy_run.
3). Add common attn metadata update in MTP.
4). Addapted data update when num_speculative_tokens > 1.
5. Add a patch of MTP to adapt vllm v0.11.0.
Existing Issues:
1. When disable_padded_drafter_batch=True and running in FullGraph mode,
the data of the first-round requests in MTP is abnormal. We need to
identify the cause subsequently.
2. When disable_padded_drafter_batch=False and running in FullGraph
mode, the acceptance rate of the second and third tokens will decrease
(For example, if we set the num_speculative_tokens=3, the acceptance
rate of first token is 90%, the second is only 50% lower than 60%, the
third is only 20% lower than 30%). The reason is that the data processed
after the model runs does not match. This is a problem from another PR.
It works fine in eager and PIECEWISE mode, but has problem in FullGraph
mode. Once we have a solution, we will submit a bugfix.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
---------
Signed-off-by: anon189Ty <Stari_Falcon@outlook.com>
Drop VLLM_USE_V1 usage. This env has been removed from vLLM already.
- vLLM version: v0.11.0
- vLLM main:
83f478bb19
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
Fixes a compatible bug with `torch_npu.npu_fused_infer_attention_score`
which is discribed in
https://github.com/vllm-project/vllm-ascend/issues/4020.
@momo609 tells us this solution.
### Does this PR introduce _any_ user-facing change?
N/A
### How was this patch tested?
The environment is same with this issue,
https://github.com/vllm-project/vllm-ascend/issues/4020.
We modify the code according to
https://github.com/vllm-project/vllm-ascend/pull/3918.
And run below codes:
```python
# run with Qwen3-next-mtp
prompts = [
"Who are you?",
]
sampling_params = SamplingParams(temperature=0.0, top_p=0.95, top_k=40, max_tokens=128)
llm = LLM(model="/home/model/Qwen3-Next-80B-A3B-Instruct",
tensor_parallel_size=4,
enforce_eager=True,
distributed_executor_backend="mp",
gpu_memory_utilization=0.7,
speculative_config={
"method": "qwen3_next_mtp",
"num_speculative_tokens": 1,
},
max_model_len=4096)
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}")
```
Outputs:
```text
Prompt: 'Who are you?', Generated text: ' I am Qwen, a large-scale language model independently developed by the Tongyi Lab under Alibaba Group. I am designed to answer questions, create text such as stories, official documents, emails, scripts, and more, as well as perform logical reasoning, programming, and other tasks. If you have any questions or need assistance, feel free to let me know anytime!'
```
Now, `torch_npu.npu_fused_infer_attention_score` is compatible with
Qwen3-Next.
- vLLM version: v0.11.0
- vLLM main:
83f478bb19
Signed-off-by: drslark <slarksblood@qq.com>
