### What this PR does / why we need it?
This PR integrate suffix decoding (https://arxiv.org/abs/2411.04975)
from vllm (https://github.com/vllm-project/vllm/pull/25784)
#
Suffix Decoding is a dynamic n-gram matching method that:
1. Uses suffix trees to generate speculative tokens quickly using branch
frequency counts.
2. Can keep a history of prior model responses, which tends to work very
well with repetitive agentic use cases.
3. Can be dynamically updated with newly generated tokens, and FIFO
eviction of older requests.
#
### Does this PR introduce _any_ user-facing change?
This feature should be implemented as opt-in and remain seamless for
users who do not require suffix speculative decoding.
For users who wish to enable it, they must first install
arctic-inference:
`pip install arctic-inference
`
After installation, the suffix speculative decoding feature can be
enabled using the following speculative config:
`--speculative_config '{"method": "suffix", "num_speculative_tokens":
5}'
`
### How was this patch tested?
This PR is currently being tested on vLLM
main:83f478bb19
with PR https://github.com/vllm-project/vllm/pull/25784
In our previous testing, suffix decoding achieved a 13%-30% throughput
improvement over n-gram on the sonnet dataset, tested on vllm-ascend
v0.9.1 with concurrency ranging from 2 to 40.
- vLLM version: v0.11.2
---------
Signed-off-by: fluctlux <38945811+fluctlux@users.noreply.github.com>
### What this PR does / why we need it?
Replace pyorch implement of sampling with triton kernels
### Does this PR introduce _any_ user-facing change?
No
- vLLM version: v0.11.2
---------
Signed-off-by: Lord_of_Ironhill <suiweiyi@huawei.com>
Signed-off-by: whx-sjtu <2952154980@qq.com>
Co-authored-by: Lord_of_Ironhill <suiweiyi@huawei.com>
Co-authored-by: whx-sjtu <2952154980@qq.com>
### What this PR does / why we need it?
The previous implementation of the flashcomm2 communication domain did
not consider pp(pipeline parallel), which caused problems when enabling
pp and flashcomm2. This PR fixes this issue.
- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2
---------
Signed-off-by: zzhx1 <zzh_201018@outlook.com>
Co-authored-by: Levi-JQ <yujinqi2@huawei.com>
### 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.
I set the `non_blocking` argument to False when moving
`exceeds_max_model_len` to the CPU. From what I understand, using
`non_blocking=True` and immediately accessing the tensor on the CPU can
cause accuracy problems. However, this issue doesn't happen when
transferring data to a device. ref:
https://discuss.pytorch.org/t/should-we-set-non-blocking-to-true/38234/18
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
---------
Signed-off-by: Jade Zheng <zheng.shoujian@outlook.com>
Qwen2.5_Omni vision tower use AscendRMSNorm, which conatins a property
function. It would be override by set_forward_context(), patch
Qwen2_5OmniThinkerForConditionalGeneration func with customized
_process_image_input() and _process_video_input() to fix it.
### What this PR does / why we need it?
Fix Qwen2.5_Omni model infer image/video issue
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2
Signed-off-by: Ting FU <futing10@huawei.com>
### What this PR does / why we need it?
Add a new fusion ops to custom_op, which can cobime the torch.bmm() and
transpsose to achieve better peformance. This ops is used in mla_v1 to
replace the bmm and transpose
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
- vLLM version: v0.11.2
---------
Signed-off-by: hust17yixuan <303660421@qq.com>
In PD-separated deployment scenarios:
* MoE layers use dynamic quantization exclusively.
* For the Attention module, Prefill (P) nodes use **dynamic**
quantization, while Decode (D) nodes use **static** quantization.
In PD-mixed deployment scenarios:
* **All components fall back to dynamic quantization**, as it is
difficult to distinguish between Prefill and Decode tokens.
___
- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2
---------
Signed-off-by: SlightwindSec <slightwindsec@gmail.com>
Signed-off-by: Slightwind <slightwindsec@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Repair the problem of moe model accuracy caused by version upgrade.
Reason:
The new version adds the "reduce_output" operation after "forward_impl".
Then we have fully taken over the implementation of the FusedMoe module.
- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2
---------
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Co-authored-by: weijinqian_v1 <weijinqian@huawei.com>
Ascend scheduler was added for non chunk prefill case before, since that
the npu ops didn't work well with chunked prefill.
Now the ops with chunked prefill work better, it's time to remove the
ascend scheduler to use vLLM default scheduler.
- vLLM version: v0.11.2
---------
Signed-off-by: wangxiyuan <wangxiyuan1007@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.
- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2
---------
Signed-off-by: shenchuxiaofugui <1311027364@qq.com>
Fix model run _npu_flash_attention in _forward_prefill_no_cache hang
issue, it was caused by wrong attention mask dtype.
### How was this patch tested?
Yes, tesed on Qwen2.5-VL and Qwen2.5-Omni
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
Signed-off-by: Ting FU <futing10@huawei.com>
### What this PR does / why we need it?
qwen3-next suppot triton chunk_gated_delta_rule ops
### co-owners
@OsirisDuan
- vLLM version: v0.11.2
Signed-off-by: shiyuan680 <917935075@qq.com>
### What this PR does / why we need it?
1.In short, we renamed the existing MooncakeStoreConnector to
AscendStoreConnector and extracted the storage engine interaction logic
into a new Backend class.
Associated RFC：https://github.com/vllm-project/vllm-ascend/issues/4329
2.Fixed the issue where the number of input parameters for the connector
was incorrect, introduced in vllm 0.11.2
### Does this PR introduce _any_ user-facing change?
change MooncakeStoreConnector to AscendStoreConnector
### How was this patch tested?
- vLLM version: v0.11.2
---------
Signed-off-by: fems14 <1804143737@qq.com>
### What this PR does / why we need it?
This PR introduces support for adding custom CANN `aclnn` ops to
`vllm-ascend`, allowing users to define and use their own custom
operators.
Key changes include:
- Building and installing custom ops into the `vllm-ascend`-specified
directory
- Binding the `aclnn` op interface to the `torch.ops._C_ascend` module
- Enabling invocation of these ops within `vllm-ascend`
This PR includes a sample custom op:
`aclnnGroupedMatmulSwigluQuantWeightNzTensorList`, which is adapted from
the CANN operator
[`aclnnGroupedMatmulSwigluQuantWeightNZ`](https://www.hiascend.com/document/detail/zh/canncommercial/83RC1/API/aolapi/context/aclnnGroupedMatmulSwigluQuantWeightNZ.md).
Its input parameters `weight` and `weight_scale` now accept
`list[torch.Tensor]` (i.e., `at::TensorList`).
### Does this PR introduce _any_ user-facing change?
No.
- vLLM version: v0.11.2
---------
Signed-off-by: QianChenxi <chenxi.qian.cq@outlook.com>
### What this PR does / why we need it?
Delete equals sign in doc
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
ut
- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2
---------
Signed-off-by: herizhen <you@example.com>
Co-authored-by: herizhen <you@example.com>
### What this PR does / why we need it?
Add readme for PD separation
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
By ci
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
---------
Signed-off-by: wangxiaoteng <wangxiaoteng@huawei.com>
Signed-off-by: liziyu <liziyu16@huawei.com>
Co-authored-by: liziyu <liziyu16@huawei.com>
### What this PR does / why we need it?
- [x] Patch `Qwen2_5_VisionAttention` with
`AscendQwen2_5_VisionAttention`.
- [x] Replace `AscendQwen2_5_VisionTransformer` with
`Qwen2_5_VisionTransformer` in vllm.
- [x] Move padding logic (q/k/v and cos/sin) before FA to `forward()` of
`Qwen2_5_VisionAttention`.
- [x] Covert `cu_seqlens` in `Qwen2_5_VisionAttention` from cumulative
form to intervals and move it to cpu (compatible for npu FA).
- [x] Remove Qwen2.5-VL modeling files.
- [x] Remove Qwen2.5-VL (without padding) modeling files.
- [x] Remove related UT.
- [x] Make `set_forward_context` pluggable when getting MM embedding.
Find more details at https://github.com/vllm-project/vllm/pull/29388.
- [x] Simplify padding logic for FA.
- [x] Add patch for https://github.com/vllm-project/vllm/pull/28798.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
- [x] Functional test (eager mode)
- [x] Functional test (graph mode)
- [x] Benchmark
- vLLM version: v0.11.2
---------
Signed-off-by: shen-shanshan <467638484@qq.com>
### What this PR does / why we need it?
While using the LLM Compressor quantization tool from the VLLM community
to generate quantized weights, the VLLM Ascend engine needs to be
adapted to support the compressed tensors quantization format.
1. Add AscendCompressedTensorsConfig to replace CompressedTensorsConfig
in vllm.
2. Support CompressedTensorsW8A8 static weight.
- weight: per-channel, int8, symmetric; activation: per-tensor, int8,
symmetric.
4. Support CompressedTensorsW8A8Dynamic weight.
- weight: per-channel, int8, symmetric; activation: per-token, int8,
symmetric, dynamic.
5. Modify the override_quantization_method in AscendQuantConfig.
Co-authored-by: taoqun110 taoqun@huawei.com
Co-authored-by: chenxi-hh chen464822955@163.com
- vLLM version: v0.11.2
---------
Signed-off-by: LHXuuu <scut_xlh@163.com>
Signed-off-by: chenxi-hh <chen464822955@163.com>
Signed-off-by: chenxi-hh <32731611+chenxi-hh@users.noreply.github.com>
Co-authored-by: chenxi-hh <chen464822955@163.com>
Co-authored-by: chenxi-hh <32731611+chenxi-hh@users.noreply.github.com>
### What this PR does / why we need it?
Upgrade cann to 8.3rc2
### Does this PR introduce _any_ user-facing change?
Yes, docker image will use 8.3.RC2
- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2
---------
Signed-off-by: MrZ20 <2609716663@qq.com>
This PR introduces the `EXEC_NPU_CMD` macro, serving as an adapter layer
to simplify the invocation of `aclnn` operators on Ascend NPUs.
**Key Changes:**
* **Adapter Layer:** Added `EXEC_NPU_CMD` macro and related dependencies
to standardize `aclnn` calls.
* **Operator Support:** Integrated `grouped_matmul_swiglu_quant` as a
reference implementation to demonstrate the usage of the new macro.
---
- vLLM version: v0.11.2
---------
Signed-off-by: SlightwindSec <slightwindsec@gmail.com>
### What this PR does / why we need it?
This patch mainly doing the following things:
1. Make k8s/lws optional for multi-node testing, allowing developers to
run multi-node tests locally by actively passing in the IP addresses of
all nodes.
2. Allows passing a custom proxy script path in the config file to load
the proxy.
- vLLM version: v0.11.2
---------
Signed-off-by: wangli <wangli858794774@gmail.com>
### What this PR does / why we need it?
| | cpu envir | npu envir |
|---|---|---|
| set `SOC_VERSION` | check if `SOC_VERSION` is in dict `soc_to_device`,
if not, raise an error that can not support current chip type. | print a
warning log when `SOC_VERSION` is not equal to chip type from `npu-smi`,
same as left for others. |
| not set `SOC_VERSION` | raise an error that `SOC_VERSION` is necessary
when compiling in a cpu envir. | use chip type from `npu-smi` to compile
vllm-ascend. |
### Does this PR introduce _any_ user-facing change?
Now we must set env `SOC_VERSION` when compiling in cpu envir.
### 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: zzzzwwjj <1183291235@qq.com>
### What this PR does / why we need it?
When running 'python example.py',connection issues often occur.The
solution is to comment out the first line the code.
Complete the specific names of machines A2 and A3.
Standardize document format,a space should be added after the colon.
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
ut
- vLLM version: v0.11.2
---------
Signed-off-by: herizhen <you@example.com>
Co-authored-by: herizhen <you@example.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>
1. Run 4-card test only when single and 2-card test passed
2. rename file to make it more clear
3. remove useless pd workflow, it has been managed by nightly test
already.
- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
mkdir triton package and move triton files
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
Signed-off-by: shiyuan680 <917935075@qq.com>
### What this PR does / why we need it?
Delete useless comments.
### Does this PR introduce _any_ user-facing change?
No
- vLLM main:
2918c1b49c
Signed-off-by: GDzhu01 <809721801@qq.com>
Torch-npu 2.7.1 has fixed the device check bug. This patch can be
removed now.
- vLLM main:
2918c1b49c
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
