### What this PR does / why we need it?
add pcp accuracy e2e test case
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: weiguihua2 <weiguihua2@huawei.com>
### What this PR does / why we need it?
unblock CI on suffix spec decoding
### How was this patch tested?
CI passed with existing test.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: MengqingCao <cmq0113@163.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?
For single node test, the lack of a retry mechanism for accessing
ModelScope resulted in an HTTP 400 error sometimes. I recommend using a
local offline cache instead.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: wangli <wangli858794774@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?
In this PR, DispatchGmmCombineDecode add an optional input
x_active_mask, with which
only token masked True will be dispatched and handle.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: wangqiankun <wangqiankun13@huawei.com>
RFC: https://github.com/vllm-project/vllm-ascend/issues/4629
Reason:
The metadata data class contains an excessive number of variables. We
will inherit the metadata of the community and simultaneously remove
some variables that are no longer needed at present.
Todo:
1. remove attn_state partly.
- 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?
This PR provides an introduction to the Qwen3-VL-235B-A22B-Instruct
model, details on the features supported by the model in the current
version, the model deployment process, as well as methods for
performance testing and accuracy testing.
With this document, the deployment and testing of the
Qwen3-VL-235B-A22B-Instruct model can be implemented more easily.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: luluxiu520 <l2625793@outlook.com>
### What this PR does / why we need it?
This patch purpose to
1. add a section on os point of perf tune doc
2. Set some default env in the image for performance
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: wangli <wangli858794774@gmail.com>
### What this PR does / why we need it?
In the past time, we used a hybrid architecture cross-compilation
approach for image building. This method had a problem:
cross-compilation performance was very poor, leading to extremely long
build times(abort 4h) and even a probability of failure(see
https://github.com/vllm-project/vllm-ascend/actions/runs/20152861650/job/57849208186).
Therefore, I recommend using a separate architecture build followed by
manifest merging, which significantly reduces image build time(20min).
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: wangli <wangli858794774@gmail.com>
### What this PR does / why we need it?
Now `VLLM_ASCEND_ENABLE_NZ` will have three options:
0: disable nz;
1: only quant case enable nz;
2: enable nz as long as possible;
And `VLLM_ASCEND_ENABLE_NZ`=1 by default.
All cases are shown in the table below:
| | W4A4 | W4A8 | W8A8 | fp16/bf16 | fp32 |
|---|---|---|---|---|---|
| trans nz | can't support nz | trans nz by default | trans nz by
default | trans nz when VLLM_ASCEND_ENABLE_NZ is 2 | can't support nz |
| transpose | only support not transpose case | only support transpose
case | only support transpose case | linear: only support not transpose
case<br>gmm: only support transpose case | same to fp16/bf16 |
Some exceptional cases:
1. MLAPO op need to do some additional processing on the weights,
including trans nz. If use MLAPO op, some weight will be transformed to
nz forcely;
2. MLA/SFA's weight `W_UV` will be used by op
`torch.ops._C_ascend.batch_matmul_transpose`, and this op can't support
nz currently;
### Does this PR introduce _any_ user-facing change?
Now fp16/bf16 weight will not trans nz by default.
### How was this patch tested?
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: zzzzwwjj <1183291235@qq.com>
vLLM version: v0.11.0
vLLM main: vllm-project/vllm
### What this PR does / why we need it?
Fix the precision issue of the LoRA feature in vllm-ascend.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
```bash
pytest tests/lora/test_llama_tp.py::test_llama_lora -s
```
<img width="1319" height="879" alt="lora_test"
src="https://github.com/user-attachments/assets/2a0b2325-5b05-4bbc-ac03-a7c9f0ad9d4c"
/>
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: hukongyi <hukongyi@cmbchina.com>
### What this PR does / why we need it?
Deepseekv3.1、DeepSeekR1 doc enhancement
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: 1092626063 <1092626063@qq.com>
### What this PR does / why we need it?
support basic long_seq feature st
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: LookAround <lixushi@huawei.com>
### What this PR does / why we need it?
Remove Pangu Related Code
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
e2e & ut
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: weichen <calvin_zhu0210@outlook.com>
### What this PR does / why we need it?
- Renames the MoE comm enum value `MoECommType.FUSED_ALLTOALL` to
`MoECommType.FUSED_MC2` and updates all call sites.
- Updates `select_moe_comm_method` to optionally select `FUSED_MC2` on
Ascend A3 when:
- `enable_expert_parallel=True`
- quantization is `w8a8_dynamic`
- `EP <= 16`
- `dynamic_eplb` is disabled
- `is_mtp_model = False`
- Replaces the old “fused all-to-all” comm implementation with
`FusedMC2CommImpl`, using `TokenDispatcherWithMC2` /
`PrepareAndFinalizeWithMC2` and `dispatch_ffn_combine`.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: Chen Chen <0109chenchen@gmail.com>
### What this PR does / why we need it?
Add top_p,top_k in EAGLE e2e
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: zhaomingyu <zhaomingyu13@h-partners.com>
### What this PR does / why we need it?
vLLM community has integrated their MooncakeConnector. The original
scripts will now find this MooncakeConnector instead of the one from
vLLM-Ascend. All scripts that involve using the MooncakeConnector need
to be modified to another name.
### Does this PR introduce _any_ user-facing change?
Yes, users need to use a new name to load vLLM-Ascend MooncakeConnector.
### How was this patch tested?
By CI.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>
### What this PR does / why we need it?
This PR aims to fix failure of `enable_force_load_balance` caused by
missing `in_profile_run` in `dummy_run` of mtp_proposer.
### Does this PR introduce _any_ user-facing change?
N/A
### How was this patch tested?
by ci
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: Zetong Li <slippersss@126.com>
### What this PR does / why we need it?
Refactor some outdated doc
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: wangli <wangli858794774@gmail.com>
### What this PR does / why we need it?
[Nightly] Avoid max_model_len being smaller than the decoder prompt to
prevent single-node-accuray-tests from failing
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
- 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?
This PR fixes some incorrect `get_current_vllm_config` calling, which
creates empty vllm_config instead.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: Angazenn <supperccell@163.com>
### What this PR does / why we need it?
Fix VL model mooncacke PD smoke test error
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: 李少鹏 <lishaopeng21@huawei.com>
### What this PR does / why we need it?
The reason why we cannot use `self.cudagraph_batch_sizes[-1]` is that
it's actually not the max number of tokens to be padded in
`FULL_DECODE_ONLY` mode, much larger instead. And it's trimmed only
before capturing to `compilation_cases`, this really caused us lots of
trouble.
Updates the logic to ensure padding occurs only when the number of input
tokens falls within a valid uniform decode query range, improving
consistency and avoiding unnecessary padding in specific decode modes.
### Does this PR introduce _any_ user-facing change?
None.
### How was this patch tested?
None.
- 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?
1. In addition to
[#4168](https://github.com/vllm-project/vllm-ascend/pull/4168),
[#5011](https://github.com/vllm-project/vllm-ascend/pull/5011)， this PR
adds two more pattern for AddRmsnormQuant with SP enabled. The key
difference is to insert an additional `maybe_all_gather_and_maybe_unpad`
between `addrmsnorm` and `quantize`.
2. This PR also introduce another api `torch.ops.vllm.quantize`, so that
we pass `input_scale` and `input_scale_reciprocal` at the same time.
This is because `npu_add_rms_norm_quant` and `npu_quantize` requires
different `div_mode`. To avoid introducing additional reciprocal
calculation in runtime, we have to pass both of them to quantize api.
3. Removes redundant `AscendQuantRmsnorm`.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: Angazenn <supperccell@163.com>
#4257 This PR implements the dense_ffn TP of the first three layers of
the deepseek model, I have refactored this PR and used very little code
to support the implementation of this feature.
This PR adds a function `is_moe_layer` to mlp_tp, which supports MLP TP
in models with both mlp and moe, such as deepseek or chat GLM.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: zzhx1 <zzh_201018@outlook.com>
Co-authored-by: 子潜 <ziqian@U-DMKXH32D-2015.local>
Co-authored-by: chenxiao <Jaychou1620@Gmail.com>
Co-authored-by: Jade Zheng <zheng.shoujian@outlook.com>
### What this PR does / why we need it?
This PR introduces optimized Triton implementations for the
rejection_greedy_sample_kernel and expand_kernel, delivering superior
performance compared to the existing Triton implementations. The new
Triton kernels maintain full functional accuracy while delivering
significant performance improvements across various batch sizes and MTP
configurations.
### Does this PR introduce _any_ user-facing change?
Yes, this PR modifies rejection_sampler.py to use optimized Triton
kernels:
- rejection_greedy_sample_kernel is enhanced with
rejection_greedy_sample_spec_len_1_triton and
rejection_greedy_sample_triton implementations
- expand_kernel receives a performance-optimized Triton version
These changes provide substantial performance improvements while
maintaining backward compatibility
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: yuxingcyx <yuxingchen.math@gmail.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
This PR fixes a bug in the `AscendMLAImpl._v_up_proj` method where the
optimized `batch_matmul_transpose` operator was not being utilized.
**Changes:**
- Modified `_v_up_proj` method to use
`torch.ops._C_ascend.batch_matmul_transpose` operator for FP16/BF16
dtypes when available
- Added fallback path using the original `torch.bmm` implementation for
other cases
- This avoids unnecessary transpose operations and improves performance
**Why needed:**
- The previous implementation only used `torch.bmm` with multiple
transpose operations, which is less efficient
- The Ascend backend provides an optimized `batch_matmul_transpose`
operator that can handle the computation more efficiently
- This fix improves inference performance for MLA (Multi-head Latent
Attention) models on Ascend NPU
### Does this PR introduce _any_ user-facing change?
No. This is a performance optimization that maintains the same
functionality and output. Users will experience faster inference for
MLA-based models, but no API or interface changes are introduced.
The changes maintain backward compatibility with the fallback path,
ensuring correct behavior when the operator is not available or for
unsupported dtypes.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: lico67373 <918688502@qq.com>
Co-authored-by: hwhaokun <haokun0405@163.com>
Co-authored-by: weijinqian0 <1184188277@qq.com>
### What this PR does / why we need it?
This PR aim to implement model runner v2 basic framework in vllm-ascend,
the e2e function is not guaranteed by this pr.
### Does this PR introduce _any_ user-facing change?
use envs.VLLM_USE_V2_MODEL_RUNNER to decide if choose model_runenr_v2.
### How was this patch tested?
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: Ronald1995 <ronaldautomobile@163.com>
### What this PR does / why we need it?
Currently, when using pipeline parallel and pd disaggregate,
model_runner will return None on non-last-pp-rank stages in
`sample_tokens`, which will cause assert error in vllm
KVOutputAggregator on [this
line](https://github.com/vllm-project/vllm/blob/main/vllm/distributed/kv_transfer/kv_connector/utils.py#L84).
In fact, all pp workers should return a model_runner_output which
contains kv_connector_output to do aggregate in Enginecore scheduler
process to ensure all kv transfer is finished for kv cache releasing
later.
To fix this issue, this PR follows gpu_model_runner in vllm, passing
kv_connector_output in `sample_tokens` to make sure all ranks will
return a ModelRunnerOutput, in non-last-pp-rank workers, it will return
EMPTY_MODEL_RUNNER_OUTPUT with kv_connector_output.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: lidenghui <lidenghui1110@gmail.com>
### What this PR does / why we need it?
fixed fused alltoall execute all reduce, when moe_comm_type is
MoECommType.FUSED_ALLTOALL
if moe_comm_type in {MoECommType.ALLTOALL, MoECommType.MC2,
MoECommType.FUSED_ALLTOALL} \
and not shared_expert_dp_enabled():
shared_out = tensor_model_parallel_all_reduce(shared_out)
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: AlvisGong <gwly0401@163.com>
Co-authored-by: Jade Zheng <zheng.shoujian@outlook.com>
### What this PR does / why we need it?
Extracts repeated `attn_metadata[layer_name].decode` access into a
single variable to improve code readability and reduce redundancy.
Uses `getattr` with a default value to safely access the decode
attribute, making the code more defensive against potential attribute
errors.
### Does this PR introduce _any_ user-facing change?
None.
### How was this patch tested?
None.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
**[RFC]: Elastic Scaling Support for P/D Instances Based on KV Pool:**
https://github.com/vllm-project/vllm-ascend/issues/3380
### What this PR does / why we need it?
Support elastic scaling for P/D instances based on mooncake conncetor
deplayment.
**Support API routes**
* `/instances/add`: add prefill nodes or decode nodes to the list.
* `/instances/remove`: remove prefill nodes or decode nodes from the
list.
**Support functions**
* Support **adding** prefill nodes or decode nodes.
- If prefill or decode server deployed **after the proxy deployed**,
server can use `/instances/add` API to join the proxy server. The
prefill server or decode server sends a signal to the proxy server, and
the proxy server will check the status of the node util the node is
available.
* Support **removing** prefill nodes or decode nodes:
- Support using `/instances/remove` API to **delete the node** from the
proxy server.
### Does this PR introduce _any_ user-facing change?
For
`examples/disaggregated_prefill_v1/load_balance_proxy_server_example.py`:
**Add 2 params**
When adding nodes to the proxy, the proxy will wait the nodes to be
started util retrying a certain of times.
| name | type | default | help |
| ----- | ---- | ---- | ---- |
| max-waiting-retries | int | 3 | Maximum number of retries for waiting
nodes to be started |
| waiting-retry-interval | float | 10 | Check interval (seconds) for
waiting nodes to be started |
For example:
```shell
python load_balance_proxy_server_example.py \
--host 0.0.0.0 --port 9000 \
--prefiller-hosts 127.0.0.1 127.0.0.1 \
--prefiller-ports 8100 8101 \
--decoder-hosts 127.0.0.1 127.0.0.1 \
--decoder-ports 8200 8201 \
--max-waiting-retries 3 \
--waiting-retry-interval 10
```
**Add 2 API routings**
* Add instances: `instances/add`
For example, add 2 prefiller instances:
```shell
curl -X POST http://localhost:9000/instances/add \
-H "Content-Type: application/json" \
-d '{
"type": "prefill",
"instances": ["127.0.0.1:8102", "127.0.0.1:8103"]
}'
```
Response:
```shell
{"message": "add prefill instances: ['127.0.0.1:8102', '127.0.0.1:8103'].", "current_prefill_instances": ['127.0.0.1:8100', '127.0.0.1:8101', '127.0.0.1:8102', '127.0.0.1:8103'], "current_decode_instances": ['127.0.0.1:8200', '127.0.0.1:8201']}
```
If the node '127.0.0.1:8103' has not benn started:
```shell
{"message": "add prefill instances: ['127.0.0.1:8102']. Instances ['127.0.0.1:8103'] are waiting to be added.", "current_prefill_instances": ['127.0.0.1:8100', '127.0.0.1:8101', '127.0.0.1:8102'], "current_decode_instances": ['127.0.0.1:8200', '127.0.0.1:8201']}
```
* Remove instances: `instances/remove`
For example, remove 1 decoder instance:
```shell
curl -X POST http://localhost:9000/instances/remove \
-H "Content-Type: application/json" \
-d '{
"type": "decode",
"instances": "127.0.0.1:8201"
}'
```
Response:
```shell
{"message": "remove decode instances: ['127.0.0.1:8201'].", "current_prefill_instances": ['127.0.0.1:8100', '127.0.0.1:8101'], "current_decode_instances": ['127.0.0.1:8200']}
```
### How was this patch tested?
Run proxy and using `/instances/add` API to add nodes and
`/instances/remove` API to remove nodes
* vLLM version: v0.11.0.rc3
* vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0.rc3
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: yuxinshan <syx_ctyg@126.com>
Signed-off-by: CalvinXKY <kyxiezju@163.com>
### What this PR does / why we need it?
This PR add w4a8 accuracy testcase for e2e test
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
By running the test
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: cuikai (C) <c00827167@china.huawei.com>
Co-authored-by: cuikai (C) <c00827167@china.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?
add qwen3 reranker tutorials
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.12.0
---------
Signed-off-by: TingW09 <944713709@qq.com>
### What this PR does / why we need it?
We will expose the enabling switch for npugraph_ex to better facilitate
subsequent optimization.
### Does this PR introduce _any_ user-facing change?
Previously, the enable_npugraph_ex switch would trigger an error; now we
have removed the error reporting mechanism to better facilitate
subsequent optimization efforts.
Basic functionalities are available in CANN and torch_npu for Q3, while
advanced optimizations will depend on the Q4 release.
### How was this patch tested?
llm =LLM(
model=model,
enforce_eager=False ,
additional_config={
"enable_npugraph_ex": True
},
compilation_config={
"cudagraph_mode": "FULL_DECODE_ONLY",
"cudagraph_capture_sizes": [16],
},
}
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: p00465316 <panchao13@huawei.com>
Co-authored-by: p00465316 <panchao13@huawei.com>
Co-authored-by: weijinqian0 <1184188277@qq.com>
### What this PR does / why we need it?
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: 李少鹏 <lishaopeng21@huawei.com>
### What this PR does / why we need it?
Synchronize the host query_start_loc with device values to prevent shape
mismatches when not enable async scheduling.
### Does this PR introduce _any_ user-facing change?
None.
### How was this patch tested?
None.
- 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?
delete sekf.in_profile_run in model_runner to make EPLB works as expect
### Does this PR introduce _any_ user-facing change?
NO
### How was this patch tested?
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: zhenwenqi2024 <zhenwenqi_2022@qq.com>
Signed-off-by: Mengqing Cao <cmq0113@163.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>
