### What this PR does / why we need it?
vllm-ascend support Ascend950 with Qwen dense model
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: wangyao <iwangyao@outlook.com>
Co-authored-by: weijinqian0 <1184188277@qq.com>
### What this PR does / why we need it?
The first commit support `FULL_DECODE_ONLY`:
- Update `AscendSFAMetadataBuilder` to use `num_input_tokens` for
slicing slots and positions, ensuring fixed tensor shapes.
- Implement padding logic for `query_start_loc` in `NPUModelRunner` to
support uniform decode in full graph mode, aligning with GPU runner
behavior.
- Adjust MLA cosine cache allocation to occur independently of graph
mode and switch to using device-resident sequence lengths for attention
metadata.
- Remove redundant slicing of hidden states and outputs in
`AscendSFAImpl` and optimize `sin`/`cos` cache updates.
The second commit take MTP into account:
- Update `AscendSFAMetadataBuilder` to use `num_input_tokens` for
slicing slots and positions, ensuring fixed tensor shapes.
- Implement padding logic for `query_start_loc` in `NPUModelRunner` to
support uniform decode in full graph mode, aligning with GPU runner
behavior.
- Adjust MLA cosine cache allocation to occur independently of graph
mode and switch to using device-resident sequence lengths for attention
metadata.
- Remove redundant slicing of hidden states and outputs in
`AscendSFAImpl` and optimize `sin`/`cos` cache updates.
And the rest of them are just bugfix.
### Does this PR introduce _any_ user-facing change?
None.
### How was this patch tested?
Test cases needed.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: Yizhou Liu <liu_yizhou@outlook.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?
this pr aims to support async_scheduling for mtp, which refer to vllm pr
https://github.com/vllm-project/vllm/pull/24799.
and this pr fix some synchronize problem in vllm-ascend.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: Ronald1995 <ronaldautomobile@163.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
RFC: https://github.com/vllm-project/vllm-ascend/issues/4629
Reason：
The functions related to Cp differ significantly from those of normal
Attention, but the coupling is quite severe.
Steps：
Isolate PCP and DCP
(1) Forward class extraction (100%)
(2) Metadata coupling processing
(3) Builder processing
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Co-authored-by: weijinqian_v1 <weijinqian@huawei.com>
### What this PR does / why we need it?
Due to the requirement of the FIA operator that the **query.shape[0]**
must match **actual_seq_len[-1]**, in graph mode and multi-DP scenarios,
the query is padded to the size of **num_input_token**. This leads to
validation errors during tiling in the operator. However, since the
padding is applied at the end of the query, it does not affect the
actual execution result of the operator, and the precision remains
unaffected.
<img width="2434" height="49" alt="image"
src="https://github.com/user-attachments/assets/63520816-fbc3-4382-82b9-89dbb1492f6c"
/>
Our modification padding both **actual_seq_len** and
**actual_seq_len_kv** to resolve the validation issue in the operator.
### 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: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
Co-authored-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.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>
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>
remove get_metadata_cls. It's only used for V0 engine and 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?
The current library only supports the FullDecodeOnly graph mode, which
enables full graph execution during the decode. This PR extends support
to allow full graph execution in both the prefill and decode, referred
to as FULL graph mode.
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
Signed-off-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
Co-authored-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
### What this PR does / why we need it?
1、qwen GQA attention_v1 optim
2、DeepSeek MLA refactor, all gather q -> all gather kv
3、modelrunner refactor for chunk prefill, we remove some code not use
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
---------
Signed-off-by: LookAround <lixushi@huawei.com>
Signed-off-by: Delphine-Nic <tanwenqin@huawei.com>
Co-authored-by: Delphine-Nic <tanwenqin@huawei.com>
### What this PR does / why we need it?
ChunkPrefill now can support Long Sequence Feature Pcp&Dcp
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
CI tests passed with self-test
- vLLM version: v0.11.0
- vLLM main:
83f478bb19
---------
Signed-off-by: Apocalypse990923-qshi <qiushixu@usc.edu>
Signed-off-by: Delphine-Nic <tanwenqin@huawei.com>
Co-authored-by: Delphine-Nic <tanwenqin@huawei.com>
Co-authored-by: Delphine-Nic <3834144971@qq.com>
### What this PR does / why we need it?
In the DCP-PCP graph mode scenario, there is a shape issue with multiple
batches. This PR fixes this problem.
- vLLM version: v0.11.0
- vLLM main:
83f478bb19
---------
Signed-off-by: weiguihua2 <weiguihua2@huawei.com>
### What this PR does / why we need it?
Adapts mtp function to Qwen3-next.
- vLLM version: v0.11.0
- vLLM main:
83f478bb19
Signed-off-by: drslark <slarksblood@qq.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>
### What this PR does / why we need it?
1、in attention_v1 module, convert bsnd t0 tnd when pcp and dcp
2、fix tochair bug: service startup problem
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.11.0
- vLLM main:
83f478bb19
Signed-off-by: weiguihua2 <weiguihua2@huawei.com>
### What this PR does / why we need it?
1、revert TND modify when dcp pcp, which is introduced by
f57bdb09fc
2、deal aclgraph pad border issue
- vLLM version: v0.11.0
- vLLM main:
83f478bb19
Signed-off-by: weiguihua2 <weiguihua2@huawei.com>
### What this PR does / why we need it?
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?
Upgrade torch-npu to the official release version 2.7.1
- vLLM version: v0.11.0
- vLLM main:
83f478bb19
---------
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
We have optimized the performance of long sequences：First,Modify the
input data format for attention calculation. Instead of using the
original BSND format, remove the logic for converting between TND and
BSND, and directly adopt the TND format.
The TND input format can be directly reused, which shortens the data
flow path. Converting to BSND is an unnecessary processing step.Second,
we switched the output update of the concatenated small operators to the
npu_attention_update fusion operator to improve performance.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.11.0rc3
- vLLM main:
c9461e05a4
---------
Signed-off-by: pichangping <1337510399@qq.com>
### What this PR does / why we need it?
dcp pcp support full aclgraph, including mla attention_v1
- vLLM version: v0.11.0rc3
- vLLM main:
c9461e05a4
Signed-off-by: weiguihua2 <weiguihua2@huawei.com>
### What this PR does / why we need it?
The cache for MLA decode graph parameters was holding strong references
to tensors, preventing them from being garbage collected and leading to
increased memory usage.
This change wraps the cached tensors in weak references, allowing them
to be deallocated when no longer in use and reducing overall memory
pressure.
### Does this PR introduce _any_ user-facing change?
None.
### How was this patch tested?
None.
- vLLM version: v0.11.0rc3
- vLLM main:
c9461e05a4
---------
Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
### What this PR does / why we need it?
Remove codes of dbo.
Currently, vLLM has supported dbo with pr:
https://github.com/vllm-project/vllm/pull/23693.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.11.0rc3
- vLLM main:
17c540a993
Signed-off-by: zzzzwwjj <1183291235@qq.com>
### What this PR does / why we need it?
This PR refactors the Ascend attention implementation to align with
vLLM's core interfaces, simplifying the code and improving
maintainability.
### Key Changes:
* **Align with vLLM's Attention Interface**: The `forward` method
signature in `AscendAttentionBackendImpl` now matches the base
`AttentionImpl` in vLLM, removing the custom `trace_flag`.
* **Enable Opaque Attention Operator**: By adding `opaque_attention_op`
to `AscendPlatform`, we allow vLLM to wrap our attention kernel in its
standard `vllm.unified_attention_with_output` operator. This avoids the
need for a custom call path.
* **Remove Obsolete Code**:
* The custom op `vllm.unified_ascend_attention_with_output` has been
deleted as it is now redundant.
* The `trace_flag` and its associated logic were removed, reducing code
complexity.
* An outdated quantization branch within the attention implementation
was cleaned up.
* **Improve Readability**: Renamed output variables (`output` vs.
`intermediate_output`) and added comments to clarify the in-place nature
of the attention output.
### Does this PR introduce _any_ user-facing change?
None.
### How was this patch tested?
No extra tests needed.
- vLLM version: v0.11.0rc3
- vLLM main:
17c540a993
---------
Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
### What this PR does / why we need it?
Add new npu_fused_infer_attention_score op to improve perfomance in
flash attention case.
### Does this PR introduce _any_ user-facing change?
### 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: ZYang6263 <zy626375@gmail.com>
### What this PR does / why we need it?
This PR aims to add padding logic to seq_lens、block_tables when running
in full decode scenario. Before this PR, the number of input tokens with
padding might exceeds corresponding seq_lens. For example, when running
in full decode scenario:
```
input_ids : [1, 3, 0, 0]
seq_lens: [2, 1]
query_start_loc: [0, 1, 2]
```
Here, `input_ids` is padded by 2 tokens while
`seq_lens`/`query_start_loc` are not. The mismatch between `input_ids`
and `seq_lens`/`query_start_loc` might cause some potential bugs. This
PR would change it into :
```
input_ids : [1, 3, 0, 0]
seq_lens: [2, 1, 1, 1]
query_start_loc: [0, 1, 2, 3, 4]
```
### 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: Angazenn <supperccell@163.com>
### What this PR does / why we need it?
The current implementation of FIA will introduce an `to_list` operation
for actual_seq_lengths_q and seq_lens，which comsumes extra time. These
operation can be moved earlier into `build` operation of attention
metadata.
### 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: Angazenn <supperccell@163.com>
### What this PR does / why we need it?
1.qwen3 moe uses add_rms_norm_quant op instead of 'add_rms_norm op and
quant op' during quantization scene.
2.torch_npu.add_rms_norm_quant op fixed accuracy while model weights is
quantized by anti_method m4, m4 quantization is asymmetric outlier
suppression method, it will generate none-zero norm bias,
add_rms_norm_quant op updated to add this parameter to calculate.
3. add torch-npu check
### Does this PR introduce _any_ user-facing change?
new feature works if torch_npu version >= torch_npu-2.7.1.dev20250919
### How was this patch tested?
1.no special parameters to set, no new envs to set. new feature works if
torch_npu version >= torch_npu-2.7.1.dev20250919
2.use qwen3 moe quantization model to test ,such as
Qwen3-235B-A22B-W8A8, Qwen3-30B-A3B-W8A8,
Qwen3-235B-A22B-Instruct-2507-m4 (anti_method m4)
- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0
---------
Signed-off-by: h30027576 <huangdong51@huawei.com>
### What this PR does / why we need it?
[Feat] Supports Aclgraph for bge-m3
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
```
pytest -s tests/e2e/singlecard/test_embedding.py
pytest -s tests/e2e/singlecard/test_embedding_aclgraph.py
```
to start an online server with bs 10, each batch's seq length=8192, we
set --max-num-batched-tokens=8192*10 to ensure encoder is not chunked:
```
vllm serve /home/data/bge-m3 --max_model_len 1024 --served-model-name "bge-m3" --task embed --host 0.0.0.0 --port 9095 --max-num-batched-tokens 81920 --compilation-config '{"cudagraph_capture_sizes":[8192, 10240, 20480, 40960, 81920]}'
```
For bs10, each batch's seq length=8192, QPS is improved from 85 to 104,
which is a 22% improvement, lots of host bound is reduced.
- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0
---------
Signed-off-by: xuyexiong <xuyexiong@huawei.com>
Co-authored-by: wangyongjun <1104133197@qq.com>
### What this PR does / why we need it?
Calculate in advance the workspace memory size needed for the
PagedAttention operator to avoid deadlocks during resource cleanup. This
PR requires torch_npu version 0920 or newer.
### Does this PR introduce _any_ user-facing change?
### 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: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
Co-authored-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
### What this PR does / why we need it?
In the full graph mode, since paged attention operators updates are
required, the parameters of this operators needs to be retained.
However, the tensor such as query、key cache、value cache, does not need
to be persistently saved, and we can manually release this space by
`weak_ref_tensor` to save the memory.
### Does this PR introduce _any_ user-facing change?
### 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: WithHades <244036962@qq.com>
### What this PR does / why we need it?
Adds support for capturing the Multi-Layer Attention (MLA) decode
operation into an ACL graph. This improves performance by compiling the
attention kernel for single-token decoding.
Key changes include:
- Implementing the graph capture logic for the MLA kernel, including
workspace management and parameter updates.
- Modifying the rotary embedding (RoPE) handling to use pre-allocated
tensors, which is a requirement for graph capture.
- Adding a `build_for_graph_capture` method to the MLA metadata builder
to create dummy metadata during the graph compilation phase.
Known issues:
- Currently, MTP is not supported in FULL_DECEDE_ONLY mode -- we're
working on a fix
- We are preparing to remove update_mla_attn_params with
auto_dispatch_capture
### Does this PR introduce _any_ user-facing change?
compilation_config={
"cudagraph_mode": "FULL_DECODE_ONLY",
},
### How was this patch tested?
- vLLM version: v0.11.0
---------
Signed-off-by: panchao-hub <315134829@qq.com>
Signed-off-by: p00465316 <panchao13@huawei.com>
Co-authored-by: p00465316 <panchao13@huawei.com>
Co-authored-by: Yizhou Liu <liu_yizhou@outlook.com>
we notice that torch npu 0919 doesn't work. This PR revert related
change which rely on 0919 version.
Revert PR: #3295#3205#3102
Related: #3353
- vLLM version: v0.11.0
### What this PR does / why we need it?
Calculate in advance the workspace memory size needed for the
PagedAttention operator to avoid deadlocks during resource cleanup. This
PR requires torch_npu version 0920 or newer.
### How was this patch tested?
- vLLM version: v0.11.0
---------
Signed-off-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
Co-authored-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
Upgrade vLLM to newest commit.
1. Remove the useless func get_state_cls, it has been removed from vLLM
already.
e6750d0b18
2. Fix ut broken by
6160ba4151
- vLLM version: v0.10.2
- vLLM main:
b1068903fd
---------
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
What this PR does / why we need it?
there are two sets of sp implementations for moe and dense models. One
is called sequence_parallelism, and the other is flashcomm_v1.
We did the following things：
Merge two sets of code with the same implementation into one.
Remove the implementation of sequence_parallelism, as this solution
cannot support aclgraph.
Does this PR introduce any user-facing change?
No
How was this patch tested?
e2e&ut
- vLLM version: v0.10.2
- vLLM main:
f225ea7dd9
---------
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Co-authored-by: weijinqian_v1 <weijinqian@huawei.com>
### What this PR does / why we need it?
Updates the `cudagraph_support` attribute to `aclgraph_support` to use
terminology appropriate for the Ascend platform (ACL graphs instead of
CUDA graphs).
This change also explicitly disables graph support for the MLA attention
backend.
### Does this PR introduce _any_ user-facing change?
None.
### How was this patch tested?
None needed.
- vLLM version: v0.10.2
- vLLM main:
5aeb925452
Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
### What this PR does / why we need it?
This is the follow-up PR of #2128 .
Moves graph parameter management components, including `GraphParams`,
`get_graph_params`, and `set_graph_params`, from the generic `utils.py`
to the more specific `compilation/acl_graph.py`.
Additionally, extracts the `update_attn_params` logic from the
`NPUModelRunner` class into a standalone function within the `acl_graph`
module.
This refactoring improves code organization by centralizing ACL
graph-related logic into its own dedicated module, enhancing modularity
and clarity.
### Does this PR introduce _any_ user-facing change?
None.
### How was this patch tested?
None needed.
Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
Note: This depends on [vLLM
#25161](https://github.com/vllm-project/vllm/pull/25161) and the
torch\_npu release from September 30.
### What this PR does / why we need it?
This pull request adds `FULL_DECODE_ONLY` mode for GQA/MHA models (MLA
models like DeepSeek V3/R1 are not included). Key improvements include:
* **Reduced dispatch latency:** By replaying the entire model execution
graph at once, we cut overhead compared with multiple smaller replays.
* **Stabilized multi-device performance:** Captureing the whole model as
one static graph also mitigates the dispatch fluctuations across
devices.
* **Stream/resource savings:** Consolidating graph captures frees up
streams, allowing more graphs to be captured.
**Known issues:**
1. `_npu_paged_attention` currently manages its own workspace in
`torch_npu`, which can deadlock when synchronizing during graph replay —
we’re working on a fix.
There may be other corner cases. This PR is the first in a planned
series; we’ll continue to iterate and address remaining issues in
follow-ups.
This is essentially a port of #1503 and #1677, but includes two major
changes:
1. Let `graph_dispatcher` decide the graph mode instead of hard-coding
it in the backend, which decouples Full Graph and Piecewise Graph and
could make it possible to remove dynamo.
2. Adapt to the new `attn_group` logic, but leave a small hack in
`update_graph_params`; multi-attention models may or may not be fully
supported yet.
### Does this PR introduce _any_ user-facing change?
```python
compilation_config={
"cudagraph_mode": "FULL_DECODE_ONLY",
},
```
### How was this patch tested?
Tests included.
- vLLM version: v0.10.2
- vLLM main:
9607d5eb44
---------
Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
