### What this PR does / why we need it?
This PR fixes various documentation issues and improves code examples
throughout the project.
Signed-off-by: MrZ20 <2609716663@qq.com>
### What this PR does / why we need it?
To improve the quality of certain docs by revising specific content.
### Does this PR introduce _any_ user-facing change?
None
### How was this patch tested?
- vLLM version: v0.19.0
- vLLM main:
6f786f2c50
---------
Signed-off-by: Lucky1 <144669645+verylucky01@users.noreply.github.com>
### What this PR does / why we need it?
Add a detailed 310 deployment tutorial.
### Does this PR introduce _any_ user-facing change?
NA
### How was this patch tested?
NA
---------
Signed-off-by: Tflowers-0129 <2906339855@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?
<!--
- 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 #
-->
Update DeepSeekOCR2.md for releases/v0.18.0
### 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.
-->
vLLM version: v0.18.0
vLLM main:
bcf2be9612
---------
Signed-off-by: Wangbei25 <wangbei41@huawie.com>
Signed-off-by: Wangbei25 <wangbei41@huawei.com>
Co-authored-by: Wangbei25 <wangbei41@huawie.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 #
-->
Correct the descriptive errors in the document.
### 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.
-->
doc test
---------
Signed-off-by: zjks98 <zhangjiakang4@huawei.com>
Co-authored-by: zjks98 <zhangjiakang4@huawei.com>
### What this PR does / why we need it?
Added NPU soft partitioning + cudagraph.piecewise limitation in graph
mode user guide doc.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
Signed-off-by: zzzzwwjj <1183291235@qq.com>
### What this PR does / why we need it?
fix documentation error or non-standard description in releases/v0.18.0
branch
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Documentation check.
---------
Signed-off-by: linfeng-yuan <1102311262@qq.com>
### What this PR does / why we need it?
This PR improves the readability of the documentation by fixing typos,
correcting command extensions.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Documentation changes only.
Signed-off-by: sunshine202600 <sunshine202600@163.com>
### What this PR does / why we need it?
This PR renames the environment variable VLLM_NIXL_ABORT_REQUEST_TIMEOUT
to VLLM_MOONCAKE_ABORT_REQUEST_TIMEOUT to align with the Mooncake
connector naming convention. It also updates the documentation and test
configurations to reflect this change and adjusts the suggested timeout
value in the documentation to 480 seconds for consistency.
### Does this PR introduce _any_ user-facing change?
Yes. The environment variable for configuring the abort request timeout
has been renamed. Users should update their environment settings from
VLLM_NIXL_ABORT_REQUEST_TIMEOUT to VLLM_MOONCAKE_ABORT_REQUEST_TIMEOUT.
### How was this patch tested?
The changes were verified by updating the corresponding test
configuration files and ensuring consistency across the documentation.
---------
Signed-off-by: herizhen <1270637059@qq.com>
Signed-off-by: herizhen <59841270+herizhen@users.noreply.github.com>
### What this PR does / why we need it?
This PR clarifies the CPU binding documentation for managing the
`irqbalance` service.
The previous wording only mentioned Ubuntu while the command shown is
specific to systemd-based Linux distributions. This update describes the
command as applicable to Ubuntu and other systemd-based distributions,
and adds a note for non-systemd systems to use the distribution-specific
service-management command.
### Does this PR introduce _any_ user-facing change?
No. This is a documentation-only update and does not change vLLM or
vllm-ascend runtime behavior.
### How was this patch tested?
Signed-off-by: chenchuw886 <chenchuw@huawei.com>
Co-authored-by: chenchuw886 <chenchuw@huawei.com>
### What this PR does / why we need it?
This PR introduce stricter Ascend `additional_config.layer_sharding`
validation to the 0.18 release branch so it is only accepted on
PD-disaggregated P nodes with `kv_role="kv_producer"`.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
E2E test
---------
Signed-off-by: chenchuw886 <chenchuw@huawei.com>
Co-authored-by: chenchuw886 <chenchuw@huawei.com>
### What this PR does / why we need it?
update GLM4.7 doc. Fix configuration issues,
including:VLLM_ASCEND_ENABLE_FLASHCOMM1、VLLM_ASCEND_BALANCE_SCHEDULING、VLLM_NIXL_ABORT_REQUEST_TIMEOUT
etc.
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
doc test
---------
Signed-off-by: zjks98 <zhangjiakang4@huawei.com>
Signed-off-by: aipaes <82140963+aipaes@users.noreply.github.com>
Co-authored-by: zjks98 <zhangjiakang4@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?
Fix kv pool CLI flag typo and formatting
### 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?
<!--
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: Pz1116 <zpbzpb123123@gmail.com>
### What this PR does / why we need it?
change --compilation_config to --compilation-config
change --max-model-len 133008 to --max-model-len 131072 for matching
128k
### Does this PR introduce _any_ user-facing change?
No
Signed-off-by: Yang Yuxi <907276627@qq.com>
### What this PR does / why we need it?
This PR updates the model deployment tutorial template to include a
requirement for authors to add a comment when code examples contain
version numbers. This ensures that users are prompted to use the version
appropriate for their specific environment.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
N/A (Documentation change)
---------
Signed-off-by: herizhen <1270637059@qq.com>
Signed-off-by: herizhen <59841270+herizhen@users.noreply.github.com>
### What this PR does / why we need it?
The env `VLLM_ASCEND_ENABLE_FUSED_MC2` should only enabled in the
decoder node during Prefill-Decode Disaggregation scenario
---------
Signed-off-by: wangli <wangli858794774@gmail.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?
- Enforce recompute scheduler only in PD-disaggregated mode.
- Enforce balance scheduling only in PD-mixed mode.
- Enforce fused MC2 only on PD-disaggregated D-side (kv_consumer).
<!--
- 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 #
-->
### Does this PR introduce _any_ user-facing change?
No
<!--
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?
By ci
<!--
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: 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 #
-->show known issues for Qwen3.5-397B
### 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.
-->NA
---------
Signed-off-by: 李少鹏 <lishaopeng21@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?
This PR updates the documentation to replace specific hardware terms
(e.g., HBM, 910B, 310P) with more generic or branded terms (e.g.,
on-chip memory, Atlas inference products) to comply with sensitive word
requirements.
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
---------
Signed-off-by: herizhen <1270637059@qq.com>
Signed-off-by: herizhen <59841270+herizhen@users.noreply.github.com>
### What this PR does / why we need it?
This PR improves the readability of the documentation by fixing typos,
correcting command extensions, and fixing broken links in the Chinese
README.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Documentation changes only.
---------
Signed-off-by: sunshine202600 <sunshine202600@163.com>
### What this PR does / why we need it?
Introduce a check to not using asynchronous communication under
`enable_dsa_cp_with_layer_shard` branch on capturing mode. This change
prevents potential stream and event issues when operating in
graph/capturing mode, ensuring safer communication practices.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
E2E test with dsv32 + FC1 + FULL_DECODE_ONLY +
kv_transfer_config(kv_both)
---------
Signed-off-by: chenchuw886 <chenchuw@huawei.com>
Co-authored-by: chenchuw886 <chenchuw@huawei.com>
### What this PR does / why we need it?
1. This PR cherry pick commit that contains current best performance at
3.5k/1.5k and 128k/1k from main to 0.18.0 branch.
2. This PR introduce MiniMax-M2.7 0day information to users.
3. To finish previous step we also changes MiniMax doc name from
MiniMax-M2.5.md to MiniMax-M2.md
---------
Signed-off-by: limuyuan <limuyuan3@huawei.com>
Co-authored-by: limuyuan <limuyuan3@huawei.com>
### What this PR does / why we need it?
This PR adds description of preemption into FAQs in vLLM-Ascend. This
FAQ stats:
- how preemption affects the performance of a vLLM server.
- how reduce the negative impacts of preemption.
The reason why we add this FAQ is that we find that the origin
description of preemption in vLLM is not very straightforward. If
preemption causes performance drop, users might not be aware that this
is caused by Preemption.
### Does this PR introduce _any_ user-facing change?
No.
Signed-off-by: Angazenn <supperccell@163.com>
What this PR does / why we need it?
This pull request performs a comprehensive cleanup of the vLLM Ascend
documentation. It fixes numerous typos, grammatical errors, and phrasing
issues across community guidelines, developer documents, hardware
tutorials, and feature guides. Key improvements include correcting
hardware names (e.g., Atlas 300I), fixing broken links, cleaning up code
examples (removing duplicate flags and trailing commas), and improving
the clarity of technical explanations. These changes are necessary to
ensure the documentation is professional, accurate, and easy for users
to follow.
Does this PR introduce any user-facing change?
No, this PR contains documentation-only updates.
How was this patch tested?
The changes were manually reviewed for accuracy and grammatical
correctness. No functional code changes were introduced.
---------
Signed-off-by: herizhen <1270637059@qq.com>
Signed-off-by: herizhen <59841270+herizhen@users.noreply.github.com>
### What this PR does / why we need it?
To avoid misleading users, the unmaintained DSV32 models, such as the
floating-point model, are deleted from the document.This PR removes the
BF16 version entries for DeepSeek-V3.2 from the documentation.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Documentation update only.
Signed-off-by: wyh145 <1987244901@qq.com>
### What this PR does / why we need it?
1. Add version notes for GLM5.
2. Add paramter modification for GLM5.
3. Add GLM5 to supported model list.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.18.0
- vLLM main:
35141a7eed
---------
Signed-off-by: yydyzr <liuyuncong1@huawei.com>
Signed-off-by: Zhu Jiyang <zhujiyang2@huawei.com>
Co-authored-by: Zhu Jiyang <zhujiyang2@huawei.com>
### What this PR does / why we need it?
This PR updates the GLM-5 documentation to include:
- Information about the first supported version
(`vllm-ascend:v0.17.0rc1`).
- Updated `--additional-config` parameters to use the new nested
`ascend_compilation_config` structure.
- Added `VLLM_ASCEND_BALANCE_SCHEDULING` environment variable to
deployment scripts.
- Improved formatting of deployment steps.
- A new "Notice" section explaining optimization environment variables
(`VLLM_ASCEND_ENABLE_FLASHCOMM1`, `VLLM_ASCEND_ENABLE_FUSED_MC2`,
`VLLM_ASCEND_ENABLE_MLAPO`).
- A "Best Practices" section for prefill-decode disaggregation.
- An "FAQ" section addressing common tokenizer issues and function
calling configuration.
### Does this PR introduce _any_ user-facing change?
No, this is a documentation-only update.
### How was this patch tested?
Documentation changes were verified for correctness and formatting.
---------
Signed-off-by: Zhu Jiyang <zhujiyang2@huawei.com>
### What this PR does / why we need it?
Update docs of Kimi-K2.5 for 0.18.0rc1
backport of #7901
---------
Signed-off-by: LoganJane <loganJane73@hotmail.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?
- Add `default_kv_lease_ttl` to the `mooncake.json` example in the KV
Pool guide.
- Document `default_kv_lease_ttl` semantics and clarify that it should
be larger than `ASCEND_CONNECT_TIMEOUT` and `ASCEND_TRANSFER_TIMEOUT`.
- Add `HCCL_RDMA_TIMEOUT` explanation for Mooncake RDMA retransmission
timeout, including the recommended constraint note.
- Add `HCCL_RDMA_TIMEOUT=16` to relevant KV Pool environment setup
examples for consistency.
<!--
- 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 #
-->
### 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?
<!--
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: Pz1116 <zpbzpb123123@gmail.com>
### What this PR does / why we need it?
Triton-ascend occasionally encounters compilation errors, which is a
known issue in triton-ascend 3.2.0. However, we want to use the official
version rather than the development version, so we only changed the
triton-ascend version in the Dockerfile and added a FAQ to explain this
issue.
---------
Signed-off-by: MengqingCao <cmq0113@163.com>
### What this PR does / why we need it?
1. Allow PR triggers on `*-dev` and `releases/v*` branches for nightly
test workflows.
2. fix image-tag in doc
---------
Signed-off-by: hfadzxy <starmoon_zhang@163.com>
### What this PR does / why we need it?
This PR adds support for hierarchical communication for `dispatch_v2`
and `combine_v2` MoE operations. This is achieved by introducing a new
configuration `enable_mc2_hierarchy_comm`. When enabled, the
communication algorithm is set to "hierarchy", which support mc2 op comm
between two super pod.
The changes include:
- Adding `enable_mc2_hierarchy_comm` to `AscendConfig`.
- Modifying `TokenDispatcherWithMC2` to pass `comm_alg: "hierarchy"` to
the underlying `torch_npu` ops when the new config is enabled.
- Adding validation to ensure that this feature is only used with
compatible PTA/CANN versions and is not used with the conflicting
`fused_mc2` op.
- Updating `is_hierarchical_communication_enabled` to respect the new
configuration flag.
### Does this PR introduce _any_ user-facing change?
Yes, this PR introduces a new user-facing configuration option
`enable_mc2_hierarchy_comm` in `additional_config` to enable
hierarchical communication for MoE.
### How was this patch tested?
- vLLM version: v0.18.0
Signed-off-by: zzzzwwjj <1183291235@qq.com>
### What this PR does / why we need it?
Support an new load format: RFORK
For implementation details of this feature, please refer to #7441
### Does this PR introduce _any_ user-facing change?
add an new options for load-format: rfork
e.g.
```bash
vllm serve /workspace/models/Qwen3-8B --load-format rfork
```
### How was this patch tested?
- vLLM version: v0.17.0
- vLLM main:
4034c3d32e
Signed-off-by: Marck <1412354149@qq.com>
### What this PR does / why we need it?
This PR adds enable_sparse_c8 option in configuration options
- vLLM version: v0.18.0
- vLLM main:
ed359c497a
Signed-off-by: rjg-lyh <1318825571@qq.com>
### What this PR does / why we need it?
2nd PR for https://github.com/vllm-project/vllm-ascend/issues/5712,
extend SP to VL MoE models.
### Does this PR introduce _any_ user-facing change?
remove `sp_threshold` in additional config and reuse `sp_min_token_num`
from vLLM.
### How was this patch tested?
- Model: Qwen3-VL-30B-A3B,
- TP4 DP2
- 100 reqs
- max concurrency 1
| Seq length | Mean TTFT (ms) main | Mean TTFT (ms) this PR |
|------------|---------------------|------------------------|
| 4k | 429.40 | 323.3 |
| 16k | 1297.01 | 911.74 |
- vLLM version: v0.16.0
- vLLM main:
4034c3d32e
---------
Signed-off-by: realliujiaxu <realliujiaxu@163.com>
### What this PR does / why we need it?
Main2main Upgrade vllm commit to 0320 17:00
1. fix vllm refactored `_moe_forward` to call
`runner.forward_impl_chunked()` when `runner.use_dp_chunking` is True.
vllm PR:"[MoE Refactor] DefaultMoERunner simplification
[#33049](https://github.com/vllm-project/vllm/pull/33049)"
2.fix vllm moved the call to `self._set_compile_ranges()` in
`VllmConfig.__post_init__` from **before** `check_and_update_config()`
to **after** it (to allow platforms to lower `max_num_batched_tokens`
first). vllm PR: "fix(xpu): Re-compute compile ranges after
platform-specific config updates"
[#37523](https://github.com/vllm-project/vllm/pull/37523)
### Does this PR introduce _any_ user-facing change?
NA
### How was this patch tested?
NA
- vLLM version: v0.17.0
- vLLM main:
8b6325758c
---------
Signed-off-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: Claude Code <noreply@anthropic.com>
### What this PR does / why we need it?
This PR aims to add note in doc that FULL mode is not supported in PCP
scenario.
Signed-off-by: Zetong Li <slippersss@126.com>
### What this PR does / why we need it?
Upgrade vllm commit to 2026.03.19.
1.Fix socket removed from StatelessProcessGroup. Upstream vLLM PR
[#36330](https://github.com/vllm-project/vllm/pull/36330) ("elastic_ep:
Fix stateless group port races") refactored StatelessProcessGroup and
removed the socket: socket.socket | None field. The socket ownership was
moved to a new create_tcp_store() helper instead of being stored as a
field on the dataclass.
2.fix `virtual_engine` parameter removed from `set_forward_context().
Upstream [V0 Deprecation] Deprecate virtual engine
[#37195](https://github.com/vllm-project/vllm/pull/37195)
### Does this PR introduce _any_ user-facing change?
NA
### How was this patch tested?
NA
- vLLM version: v0.17.0
- vLLM main:
8b6325758c
---------
Signed-off-by: leo-pony <nengjunma@outlook.com>
### What this PR does / why we need it?
Upgrade vllm v0.18.0 in dockerfile
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.17.0
- vLLM main:
8b6325758c
Signed-off-by: hfadzxy <starmoon_zhang@163.com>
### What this PR does / why we need it?
1. upgrade to 0.18.0
2. ensure kernel_block_sizes is int for Eagle drafter
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.17.0
- vLLM main:
8b6325758c
---------
Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>
Signed-off-by: hfadzxy <starmoon_zhang@163.com>
Co-authored-by: hfadzxy <starmoon_zhang@163.com>
### What this PR does / why we need it?
Main updates include:
- update model IDs and default model paths in serving / offline
inference examples
- adjust some command snippets and notes for better copy-paste usability
- replace `SamplingParams` argument usage from `max_completion_tokens`
to `max_tokens`（**Offline** inference currently **does not support** the
"max_completion_tokens"）
``` bash
Traceback (most recent call last):
File "/vllm-workspace/vllm-ascend/qwen-next.py", line 18, in <module>
sampling_params = SamplingParams(temperature=0.6, top_p=0.95, top_k=40, max_completion_tokens=32)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: Unexpected keyword argument 'max_completion_tokens'
[ERROR] 2026-03-17-09:57:40 (PID:276, Device:-1, RankID:-1) ERR99999 UNKNOWN applicaiton exception
```
- refresh **Qwen3-Omni-30B-A3B-Thinking** recommended environment
variable
``` bash
export HCCL_BUFFSIZE=512
export HCCL_OP_EXPANSION_MODE=AIV
```
``` bash
EZ9999[PID: 25038] 2026-03-17-08:21:12.001.372 (EZ9999): HCCL_BUFFSIZE is too SMALL, maxBs = 256, h = 2048,
epWorldSize = 2, localMoeExpertNum = 64, sharedExpertNum = 0, tokenNeedSizeDispatch = 4608, tokenNeedSizeCombine
= 4096, k = 8, NEEDED_HCCL_BUFFSIZE(((maxBs * tokenNeedSizeDispatch * ep_worldsize * localMoeExpertNum) +
(maxBs * tokenNeedSizeCombine * (k + sharedExpertNum))) * 2) = 305MB, HCCL_BUFFSIZE=200MB.
[FUNC:CheckWinSize][FILE:moe_distribute_dispatch_v2_tiling.cpp][LINE:984]
```
- fix **Qwen3-reranker** example usage to match the current **pooling
runner** interface and score output access
``` python
model = LLM(
model=model_name,
task="score", # need fix
hf_overrides={
"architectures": ["Qwen3ForSequenceClassification"],
"classifier_from_token": ["no", "yes"],
```
--->
``` python
model = LLM(
model=model_name,
runner="pooling",
hf_overrides={
"architectures": ["Qwen3ForSequenceClassification"],
"classifier_from_token": ["no", "yes"],
```
- modify **PaddleOCR-VL** parameter `TASK_QUEUE_ENABLE` from `2` to `1`
``` bash
(EngineCore_DP0 pid=26273) RuntimeError: NPUModelRunner init failed, error is NPUModelRunner failed, error
is Do not support TASK_QUEUE_ENABLE = 2 during NPU graph capture, please export TASK_QUEUE_ENABLE=1/0.
```
These changes are needed because several documentation examples had
drifted from the current runtime behavior and recommended invocation
patterns, which could confuse users when following the tutorials
directly.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
- vLLM version: v0.17.0
- vLLM main:
4497431df6
Signed-off-by: MrZ20 <2609716663@qq.com>
### What this PR does / why we need it?
Upgrade vllm commit to 0318.
Main content: Added a pre-operation for cleaning up and waiting(default
max 50s) for the completion of the clean up of the NPU memory to some
test cases that failed due to the failure to release the NPU memory in a
timely manner when the previous test cases were executed.
### Does this PR introduce _any_ user-facing change?
NA
### How was this patch tested?
NA
- vLLM version: v0.17.0
- vLLM main:
4497431df6
---------
Signed-off-by: leo-pony <nengjunma@outlook.com>
