### 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?
- [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?
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>
### 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>
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>
### 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`.
- vLLM main:
2918c1b49c
Signed-off-by: shen-shanshan <467638484@qq.com>
### What this PR does / why we need it?
**Problem**: The Qwen3Next model implementation currently imports
chunk_gated_delta_rule directly using `from ... import ...`
In frameworks like `verl`, the model file is often imported before
`vllm-ascend` initializes and applies its patches. This causes the model
to permanently hold a reference to the original (unpatched) vLLM kernel,
resulting in execution errors on Ascend devices even if the patch runs
later.
**Solution**: Changed the import style to `from vllm...ops import chunk`
and call `chunk.chunk_gated_delta_rule().`
This ensures that the function lookup happens at runtime (dynamic
dispatch), allowing the model to correctly pick up the patched function
regardless of import order.
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
Signed-off-by: zjchenn <zjchenn@gmail.com>
### What this PR does / why we need it?
Fix a bug caused by this pr:
https://github.com/vllm-project/vllm-ascend/pull/4223
The bug makes
vllm-ascend/vllm_ascend/patch/platform/patch_multiproc_executor.py patch
in a wrong way
### How was this patch tested?
Tested in a single node. When the environment DYNAMIC_EPLB is set to
true, the patch works correctly. When it's set to false, the patch do
not patch
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
Signed-off-by: 白永斌 <baiyongbin3@h-partners.com>
Co-authored-by: 白永斌 <baiyongbin3@h-partners.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
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
---------
Signed-off-by: wujinyuan1 <wjy9595@qq.com>
Co-authored-by: wujinyuan1 <wjy9595@qq.com>
### What this PR does / why we need it?
vllm-ascend need to dump data during model execution to debug some
precision problems, here msprobe provide the corresponding abilities, so
msprobe will join vllm-ascend to make debug easier
### Does this PR introduce _any_ user-facing change?
```
'dump_config': '/path/to/config.json'
```
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
---------
Signed-off-by: Tjh-UKN <2559659915@qq.com>
### What this PR does / why we need it?
Temporarily fix the oom issue, will update to vllm's plan later.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
e2e&ut
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
The main purposes of this PR are as follows:
1. Remove the multicast-related code;
Reason:
1. In the scenario like a2 Dual-System Back-to-Back Networking，the
performance is worse than all_gather. Before the modification, in e2e
test, it was 3 tps; after the modification, it is 10 tps.
2. At the same time, we usually enable the SP feature，it is consistent
with the current logic.
3. The advantage of broadcast communication lies in the fact that it
does not suffer from uneven DP load and does not require the prefill ACL
graph to be enabled. But we support prefill Acl graph recently.
So we think there is no need to maintain the multicast as one choice in
moe communication.
Performance benefits are as follows:
When not enable_flashcomm1, TTFT remains relatively stable at around
43000ms, which is approximately 15000ms faster than before the
modification.
When enable_flashcomm1, there is no diffenence, TTFT remains relatively
stable at around 29000ms.
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
---------
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Signed-off-by: weijinqian0 <1184188277@qq.com>
Co-authored-by: weijinqian_v1 <weijinqian@huawei.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>
### What this PR does / why we need it?
Remove unnecessary NPU synchronization in MTP proposer to improve
performances.
Removing this synchronization point improves pipeline efficiency by
allowing for better overlap between CPU and NPU operations. A more
proper one is already implemented in #4233
### Does this PR introduce _any_ user-facing change?
None.
### How was this patch tested?
None.
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
### What this PR does / why we need it?
fix import error for get_ip() in vllm main branch
### Does this PR introduce _any_ user-facing change?
N
### How was this patch tested?
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
---------
Signed-off-by: pz1116 <zpbzpb123123@gmail.com>
### What this PR does / why we need it?
In [#26016](https://github.com/vllm-project/vllm/pull/26016), vllm
change the `cudagraph_capture_sizes` to be in ascending order. This PR
fixes related issues caused by this.
### Does this PR introduce _any_ user-facing change?
No.
### 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?
Eplb Verify Fix
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
---------
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>
This PR is used to fix mooncake_connector in pcp/dcp case. When
executing function update_done_task_count, it is necessary to ensure
that both pcp/dcp and TP ranks have finished transferring KV cache.
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
---------
Signed-off-by: wangxiaochao <w00642655@china.huawei.com>
Co-authored-by: wangxiaochao <w00642655@china.huawei.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?
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
Signed-off-by: shen-shanshan <467638484@qq.com>
### What this PR does / why we need it?
Add information on the scope of EPLB support.
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
---------
Signed-off-by: shenchuxiaofugui <1311027364@qq.com>
### What this PR does / why we need it?
Redundant experts bugfix
### Does this PR introduce _any_ user-facing change?
After configuring the path for experts_map, users do not need to
configure iinit_redundancy_expert.
### How was this patch tested?
The accuracy of EPLB was tested with and without the use of redundant
experts.
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
---------
Signed-off-by: shenchuxiaofugui <1311027364@qq.com>
### What this PR does / why we need it?
Support the Qwen3-Next-80B-A3B-Instruct quantization model and Fix the
NZ issue. Triton kernel doesn't support data format nz, thus we skip
converting weight to nz on layer `conv1d`
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
---------
Signed-off-by: IncSec <1790766300@qq.com>
### What this PR does / why we need it?
Currently, the MTP model still runs in eager in full graph mode. This PR
adapts the MTP with the full graph capture and execution. When the graph
mode is set to "FULL_DECODE_ONLY", the MTP will run in full-graph to
improve the performance.
The change in both disable_padded_drafter_batch is True and False case
include:
1. Add _mtp_graph_params in acl_graph.py to isolate the data of main
model and the data of MTP.
2. Padding some metadata in mla_v1.py when in fullgraph mode.
3. Fixed the essential data address that will be used in model.forward.
4. Adapted according to the aclgraph capture framwork:
1). Rebuild MTP model with ACLGraphWrapper.
2). Add common attn metadata when start capture in MTP dummy_run.
3). Add common attn metadata update in MTP.
4). Addapted data update when num_speculative_tokens > 1.
5. Add a patch of MTP to adapt vllm v0.11.0.
Existing Issues:
1. When disable_padded_drafter_batch=True and running in FullGraph mode,
the data of the first-round requests in MTP is abnormal. We need to
identify the cause subsequently.
2. When disable_padded_drafter_batch=False and running in FullGraph
mode, the acceptance rate of the second and third tokens will decrease
(For example, if we set the num_speculative_tokens=3, the acceptance
rate of first token is 90%, the second is only 50% lower than 60%, the
third is only 20% lower than 30%). The reason is that the data processed
after the model runs does not match. This is a problem from another PR.
It works fine in eager and PIECEWISE mode, but has problem in FullGraph
mode. Once we have a solution, we will submit a bugfix.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
---------
Signed-off-by: anon189Ty <Stari_Falcon@outlook.com>
