### What this PR does / why we need it?
Previously, the dummy run executed compute_logits only once, regardless
of num_speculative_tokens. This caused execute_model to hang on
compute_logits when lm head tensor parallelism exceeded 1. The fix
ensures compute_logits executes correctly during dummy run, matching
num_speculative_tokens.
Signed-off-by: zouyida2052 <zouyida2002@gmail.com>
### What this PR does / why we need it?
The expert mapping table and weights of the dynamic EPLB were not
updated, causing the accuracy to be correct but not effective. This bug
has now been fixed.
If it was tested in a way different from regular unit tests, please
clarify how you tested step by step, ideally copy and paste-able, so
that other reviewers can test and check, and descendants can verify in
the future.
Signed-off-by: shenchuxiaofugui <1311027364@qq.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?
disable NZ for float weight case. This is only a quick fix for dev
branch.
For main branch, we'll consider more case to make it more common.
### Does this PR introduce _any_ user-facing change?
<!--
Note that it means *any* user-facing change including all aspects such
as API, interface or other behavior changes.
Documentation-only updates are not considered user-facing changes.
-->
### How was this patch tested?
qwen2.5 32B
<img width="441" height="221" alt="image"
src="https://github.com/user-attachments/assets/7ae18ffd-1ce2-43d9-9960-be45250ad0da"
/>
---------
Signed-off-by: 刘哲续 <liuzhexu1@huawei.com>
Co-authored-by: 刘哲续 <liuzhexu1@huawei.com>
### What this PR does / why we need it?
To fix ops test, where `model_config` has been set to `None` and doesn't
has `hf_config` attribute, we have added a check for `model_config` to
guarantee it is not `None_Type`.
cherry-pick from main:
https://github.com/vllm-project/vllm-ascend/pull/4384.
Signed-off-by: shen-shanshan <467638484@qq.com>
### What this PR does / why we need it?
When cudagraph_mode is set to FULL_DECODE_ONLY, if dp > 1, the dummy-run
process will be triggered. When calling the update_attn_params function,
the num_tokens parameter needs to be passed, and this value is obtained
through positions.shape[0]. However, the multimodal model uses mRope
(multi-dimensional rotary positional embeddings), which causes the shape
of positions to be 2. As a result, the value obtained from
positions.shape[0] is incorrect. We solve this problem by replacing
positions.shape[0] with num_tokens.
### Does this PR introduce _any_ user-facing change?
NO
### How was this patch tested?
vLLM version: v0.11.0rc3
vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0
---------
Signed-off-by: wujinyuan1 <wjy9595@qq.com>
Co-authored-by: wujinyuan1 <wjy9595@qq.com>
### What this PR does / why we need it?
Enable force_load_balance in aclgraph, solving OOM issues.
pick from https://github.com/vllm-project/vllm-ascend/pull/4366
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
e2e & ut
Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
### What this PR does / why we need it?
add single node PD disaggregation instructions for Qwen 2.5VL model.
### Does this PR introduce _any_ user-facing change?
no
---------
Signed-off-by: mazhixin <mazhixin7@huawei.com>
Signed-off-by: mazhixin000 <mazhixinkorea@163.com>
Co-authored-by: mazhixin <mazhixin7@huawei.com>
### What this PR does / why we need it?
Eplb Verify Fix
---------
Signed-off-by: shenchuxiaofugui <1311027364@qq.com>
Signed-off-by: LI SHENGYONG <49200266+shenchuxiaofugui@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
### What this PR does / why we need it?
For better usability, add multimodal audio to vllm compiling in
dockerfile defaultly.
Image size will increase only 2.xM.
Signed-off-by: Ting FU <futing10@huawei.com>
### What this PR does / why we need it?
Remove redundant workflows， just maintain a separate workflow which
setting up on the main branch to control the execution of each branch,
instead of running each branch simultaneously, thus reducing resource
waste.
Signed-off-by: wangli <wangli858794774@gmail.com>
### What this PR does / why we need it?
Add error log for VL models when enabling
`VLLM_ASCEND_ENABLE_FLASHCOMM1=1` or `VLLM_ASCEND_ENABLE_FLASHCOMM=1`
(for backward compatibility).
This is a temporary fix for
https://github.com/vllm-project/vllm-ascend/issues/4132.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
Signed-off-by: shen-shanshan <467638484@qq.com>
### What this PR does / why we need it?
This dev version of #4199 .
Currently, the default `cudagraph_capture_size` in vLLM is `[1, 2, 4 ,8
,16 ,24 ,... , max_capture_size]`. However, this is not always the best
choice on different situations. This PR aims to change the default
setting when running Qwen3-MoE on full dp (`dp_size > 1` && `tp_size ==
1`) setting, which is usually applied in Large-Scale EP.
old :
`[1, 2, 4 ,8 ,16 ,24 ,... , max_capture_size]`
new:
`[1, 2, 5 ,10 ,15, 16 ,24 ,... , max_capture_size]`
This is mainly because the performance of `_npu_paged_attention` op
degrades dramatically on old settings. We hope to provide better
performance if users do not set specific `cudagraph_capture_size`.
### Does this PR introduce _any_ user-facing change?
The default `cudagraph_capture_size` is modified in above cases.
However, if `cudagraph_capture_size` has already set by users, this PR
won't have any influence on this.
### How was this patch tested?
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
---------
Signed-off-by: Angazenn <supperccell@163.com>
### What this PR does / why we need it?
avoid mrope fusion op when running qwen25vl on x86 machine
---------
Signed-off-by: 李少鹏 <lishaopeng21@huawei.com>
### What this PR does / why we need it?
pick from : https://github.com/vllm-project/vllm-ascend/pull/2958
Past：
npu_moe_gating_top_k can only support 'group_count=256' pattern
Now：
1、npu_moe_gating_top_k support all size of group_count
2、the functionality of `torch_npu.npu_moe_gating_top_k_softmax` are
included in `torch_npu.npu_moe_gating_top_k`
CANN: depends on 8.3.RC1
Performance：
1. GLM4.5-w8a8, TPS improve 6%
2. Qwen3, the same as before
Signed-off-by: 1092626063 <1092626063@qq.com>
### What this PR does / why we need it?
pd proxy support ipv6, mooncake connector check whether the IPv6 address
is used and notify the user.
---------
Signed-off-by: liziyu <liziyu16@huawei.com>
### What this PR does / why we need it?
Quick fix for missing log2phy conversion in MC2 token_dispatcher, which
has been already fixed in main branch
https://github.com/vllm-project/vllm-ascend/pull/3512.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
e2e & ut
Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
<!-- Thanks for sending a pull request!
BEFORE SUBMITTING, PLEASE READ
https://docs.vllm.ai/en/latest/contributing/overview.html
-->
### What this PR does / why we need it?
This is cherry-pick from #4097 .
Currently, we set `seq_lens` in dummy attn_metadata to be
`max_model_len` to get max workspace for attention during capturing.
However, setting it consistently to be `max_model_len` causing dummy_run
to execute a long attention when running actual inference. For example,
if there is a single req with `seqs_lens` as [8] but `max_model_len` is
131072, the whole process will be slow down by dummy_run as it execute a
fake long-seq attention. Therefore, we instead set it to max_query_len,
which is also consistent with vLLM gpu implementation.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
<!--
CI passed with new added/existing test.
If it was tested in a way different from regular unit tests, please
clarify how you tested step by step, ideally copy and paste-able, so
that other reviewers can test and check, and descendants can verify in
the future.
If tests were not added, please describe why they were not added and/or
why it was difficult to add.
-->
---------
Signed-off-by: Angazenn <supperccell@163.com>
### What this PR does / why we need it?
This pr fixes a bug introduced in #3985, which set wrong npu_stream
(possibly by mistakes in cherry-pick). I correct it and make
`update_attn_params` consistent to main branch.
### Does this PR introduce _any_ user-facing change?
No.
Signed-off-by: Angazenn <supperccell@163.com>
### What this PR does / why we need it?
- Fixes Qwen3-Next enable nz accuracy problem
---------
Signed-off-by: wxsIcey <1790571317@qq.com>
Signed-off-by: Icey <1790571317@qq.com>
### What this PR does / why we need it?
Cherry-pick #3967 from main branch. This PR reverts the changes
introduced in PR #2894 Initially, due to performance issues with the
older version of the chunked prefill ops, the default behavior was to
use the Ascend scheduler to disable the chunked prefill feature.
However, with the improvements in the performance of the new chunked
prefill ops, this interception strategy has been removed. This change
also aligns with the community's default configuration behavior.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
CI passed with new added/existing test.
Signed-off-by: rjg-lyh <1318825571@qq.com>
### What this PR does / why we need it?
In the `update_*attn_params` functions, the
`torch.npu.stream(update_stream)` context manager was previously located
inside the for-loop that updates parameters for each layer. This
resulted in redundant stream initiations for every layer, adding
unnecessary overhead.
This commit refactors the code by moving the stream context manager to
wrap the entire for-loop. This ensures that the update stream is
initiated only once per function call, rather than for each layer. This
change reduces 90us in each decode model.
update stream in every layer:
<img width="1720" height="383" alt="image"
src="https://github.com/user-attachments/assets/70e4cb69-5bc1-4180-a67d-c99132134be6"
/>
remove update stream in every layer:
<img width="1269" height="175" alt="image"
src="https://github.com/user-attachments/assets/0e290edb-b0ce-48fe-b032-1b924ade6ae5"
/>
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.11.0
- vLLM main:
83f478bb19
Signed-off-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
Co-authored-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
### What this PR does / why we need it?
cherry-pick from https://github.com/vllm-project/vllm-ascend/pull/4022
The code bug caused an empty bubble. When the npu_paged_cache_load
operator was called, it forcibly transferred seq_len2 to the device,
which triggered synchronization and interrupted the CPU operator's
launch stream.
---------
Signed-off-by: underfituu <hzhucong@163.com>
### What this PR does / why we need it?
1.Fix proxy format processing errors.
2.Layer-wise connector performance optimization
Signed-off-by: wangxiaoteng <wangxiaoteng@huawei.com>
<!-- Thanks for sending a pull request!
BEFORE SUBMITTING, PLEASE READ
https://docs.vllm.ai/en/latest/contributing/overview.html
-->
### What this PR does / why we need it?
<!--
- Please clarify what changes you are proposing. The purpose of this
section is to outline the changes and how this PR fixes the issue.
If possible, please consider writing useful notes for better and faster
reviews in your PR.
- Please clarify why the changes are needed. For instance, the use case
and bug description.
- Fixes #
-->
fix sleepmode level2 e2e test
### Does this PR introduce _any_ user-facing change?
<!--
Note that it means *any* user-facing change including all aspects such
as API, interface or other behavior changes.
Documentation-only updates are not considered user-facing changes.
-->
no
### How was this patch tested?
<!--
CI passed with new added/existing test.
If it was tested in a way different from regular unit tests, please
clarify how you tested step by step, ideally copy and paste-able, so
that other reviewers can test and check, and descendants can verify in
the future.
If tests were not added, please describe why they were not added and/or
why it was difficult to add.
-->
use e2e tests
Signed-off-by: wangx700 <wangxin700@huawei.com>
### What this PR does / why we need it?
This PR repalce the vision tower in Qwen2.5-Omni-Thinker model,
Qwen2_5_VisionTransformer, with AscendQwen2_5_VisionTransformer, which
use QKV padding for padding performance.
- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0
Signed-off-by: Ting FU <futing10@huawei.com>
### What this PR does / why we need it?
Make kv-transfer env variable take effect & Fix load-balance proxy.
Cherry Pick from #3981
---------
Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>
### What this PR does / why we need it?
add new ut case for aclgraph enable
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
ut
Signed-off-by: lilinsiman <lilinsiman@gmail.com>
### What this PR does / why we need it?
This is cherry-pick from #3986 .
This PR fixes a bug where the workspace of `_npu_paged_attention` in
setup is smaller than execution. For current implementation of
FULL_DECODE_ONLY with `_npu_paged_attention`, we use
`_npu_paged_attention_get_workspace` when capturing with `max_model_len`
as `seq_lens`. This assumes that PA with larger `seq_lens` inputs should
have larger workspace than smaller `seq_lens`. However, there are rare
cases where PA with smaller `seq_lens` incurs larger space. So I add
`get_workspace` directly into `update_attn_params`.
This change might introduce slight(≈1%) performance degradation for
small num_tokens(such as 1) in decode phase, and there is no other known
memory issues. So I think this change is acceptable. We can remove this
if new attention op (such as `npu_fused_infer_attention_score`) does not
have such problems.
Signed-off-by: Angazenn <supperccell@163.com>
### What this PR does / why we need it?
Fix#3891.
The empty of `moe_comm_method` in the above issue is due to the wrong
check for MoE models. To be specific, the method `is_moe_model` only
checks whether a text-only model is a MoE model, without considering
multi-modal models, e.g., `VL` and `Omni`.
Check the config dict recursively to find if it has a key contains
"expert", without checking the model architecture.
It is worth noting that, we can't verify a model by if it contains
`FusedMoE` module because `is_moe_model` is called somewhere before the
model loading, e.g., it's called when updating the ACLGraph config in
platform initialization.
- vLLM version: v0.11.0
- vLLM main:
83f478bb19
---------
Signed-off-by: shen-shanshan <467638484@qq.com>
This PR upgrade CANN from 8.2rc1 to 8.3rc1 and remove the CANN version
check logic.
TODO: we notice that UT runs failed with CANN 8.3 image. So the base
image for UT is still 8.2. We'll fix it later.
- vLLM version: v0.11.0
- vLLM main:
83f478bb19
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
This PR aims to fix weak memory ordering problem in share memory by
patching message queue with an additional lock. The detailed issue can
be found here https://github.com/vllm-project/vllm/issues/27858. The key
point is to use the writer lock to enforce memory fence before the ready
flag `metadata_buffer[0] = 1` is set.
This is a temporary solution, and you can use it by setting env
`SHM_BARRIER=true`. By default, we disable this modification.
### Does this PR introduce _any_ user-facing change?
`SHM_BARRIER=true` enables this change while `SHM_BARRIER=false`
disables this change. The latter is the default choice.
### How was this patch tested?
by ci
---------
Signed-off-by: Zetong Li <slippersss@126.com>
### What this PR does / why we need it?
Set adxl engine as the default Mooncake backend, because Ascend
Transport is no longer maintained.
Update README to include instructions for installing the adxl backend
Mooncake.
### Does this PR introduce _any_ user-facing change?
Users need to compile and install the mooncake backend for adxl
according to the revised README instructions.
### How was this patch tested?
By CI.
---------
Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>
### What this PR does / why we need it?
Protect the scene where the first problem occurs. The execution should
be interrupted when the video memory application fails, rather than
waiting until an illegal address is accessed.
### Does this PR introduce _any_ user-facing change?
NA
### How was this patch tested?
NA
- vLLM version: v0.11.0
- vLLM main:
83f478bb19
Signed-off-by: leo-pony <nengjunma@outlook.com>
### What this PR does / why we need it?
Fix 2 breaks of aclgraph with MTP:
1. deepseekmtp in vllm 0.11.0 does not support aclgraph and lack the
`support_torch_compile` decorator
2. There is a d2h synchornization in the original forward of mtp
predictor. The fix pr in vllm
https://github.com/vllm-project/vllm/pull/27643
As we'll fix it in vllm main, this fix pr is only needed in branch
v0.11.0-dev
The profling shows that MTP replays in aclgraph now:
<img width="1612" height="1866" alt="a7d7f04155df4ed454b7eb20a92b2e2a"
src="https://github.com/user-attachments/assets/eaa4b9ff-aeb0-416d-964f-5a06e497f155"
/>
### How was this patch tested?
<!--
CI passed with new added/existing test.
If it was tested in a way different from regular unit tests, please
clarify how you tested step by step, ideally copy and paste-able, so
that other reviewers can test and check, and descendants can verify in
the future.
If tests were not added, please describe why they were not added and/or
why it was difficult to add.
-->
---------
Signed-off-by: MengqingCao <cmq0113@163.com>
### What this PR does / why we need it?
This PR temporarily bypasses the scenario where some models in vLLM
trigger a `ValueError` during the process of storing values in
`static_forward_context` when no `prefix` is specified for the linear
layers, which is a bug in some models in vLLM. The official fix will be
addressed by submitting a PR to the vLLM community that specifies a
prefix for the linear layers in each model.
- vLLM version: v0.11.0
- vLLM main:
83f478bb19
### How was this patch tested?
CI passed with new added/existing test.
Signed-off-by: rjg-lyh <1318825571@qq.com>
