### What this PR does / why we need it?
This PR introduces the Ascend implementation of the
`dispatch_ffn_combine` kernel and wires it into the vLLM-Ascend runtime,
together with follow‑up fixes to ensure the kernel builds and runs
correctly in CI.
- Add full host and device implementation of the `dispatch_ffn_combine`
kernel under `csrc/dispatch_ffn_combine`, including tiling logic, MOE
routing helpers, and kernel utilities for quantized FFN dispatch.
- Integrate the new kernel with the PyTorch binding
(csrc/torch_binding.cpp, csrc/torch_binding_meta.cpp) and the Ascend
runtime (vllm_ascend/ascend_forward_context.py,
vllm_ascend/worker/model_runner_v1.py).
- Extend fused MoE communication and token dispatch support in
`vllm_ascend/ops/fused_moe`, adding methods/utilities needed by the new
dispatch path.
- Update quantization logic in vllm_ascend/quantization/w8a8_dynamic.py
to support the new FFN dispatch flow.
- Fix kernel build issues by adjusting `csrc/build_aclnn.sh`, CMake
configuration, and include/namespace usage in the new kernel files.
- Add an end‑to‑end nightly test
`tests/e2e/nightly/ops/test_dispatch_ffn_combine.py` and helper
utilities in `vllm_ascend/utils.py` to validate the new kernel.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.12.0
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.12.0
---------
Signed-off-by: mojave2 <chenchen145@huawei.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
Fix the issue where the qwen3 moe service cannot be started due to
upgrading the vllm version
Error info:
AttributeError: 'AscendFusedMoE' object has no attribute 'use dp
chunking'
### Does this PR introduce _any_ user-facing change?
no
- vLLM version: v0.11.2
---------
Signed-off-by: Wang Kunpeng <1289706727@qq.com>
The M4 quantization method in ModelSlim adds bias to model weights that
originally do not have a linear bias. PR #4235 supported PD-MIX
quantization and M4 quantization, adding bias to `w8a8.py` and
`w8a8_dynamic.py`, and implementing adaptations in `ops/linear.py` to
prevent it from being reset to `None` by
`self.register_parameter("bias", None)`. However, this modification
introduced an issue where the bias was still being reset to `None` in
certain scenarios, causing errors during service startup. Therefore,
support for M4 quantization is temporarily being reverted in this PR.
___
- vLLM version: v0.11.2
Signed-off-by: SlightwindSec <slightwindsec@gmail.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>
### 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>
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?
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?
In PR https://github.com/vllm-project/vllm-ascend/pull/3420, we
initially placed the quantization type (quant_type) in the MoECommMethod
class. However, since MoECommMethod follows a singleton pattern, it
couldn't accommodate scenarios where different layers in the model might
use different quantization approaches (e.g., MTP modules using
floating-point computation while the main model employs quantized
computation).
In this PR, we've moved the quantization type to the AscendFusedMoe
class and pass it as a parameter to MoECommMethod.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
```bash
export HCCL_BUFFSIZE=1024
export VLLM_VERSION=0.11.0
vllm serve /home/data/DeepSeek-R1_w8a8/ \
--data-parallel-size 2 \
--tensor-parallel-size 8 \
--enable-expert-parallel \
--served-model-name dsv3 \
--max-model-len 32768 \
--max-num-batched-tokens 4096 \
--max-num-seqs 16 \
--quantization ascend \
--trust-remote-code \
--gpu-memory-utilization 0.9 \
--speculative-config '{"num_speculative_tokens": 2, "method":"deepseek_mtp"}'
```
- vLLM version: v0.11.0
- vLLM main:
83f478bb19
---------
Signed-off-by: realliujiaxu <realliujiaxu@163.com>
### What this PR does / why we need it?
Supports generalized FlashComm2 optimization, which reduces
communication overhead, decreases RmsNorm computation, and saves one
AllGather step by replacing Allreduce operations in the Attention module
with pre-AlltoAll and post-AllGather operations (used in combination
with FlashComm1). This feature is enabled during the Prefill phase and
is recommended to be used together with FlashComm1, delivering broad
performance improvements, especially in long sequence scenarios with
large tensor parallelism (TP) configurations. Benchmark tests show that
under TP16DP1 configuration, it can improve the prefill performance of
the DeepSeek model by 8% on top of FlashComm1.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.11.0
- vLLM main:
83f478bb19
---------
Signed-off-by: zzhxx <2783294813@qq.com>
Signed-off-by: Levi-JQ <yujinqi2@huawei.com>
Co-authored-by: Levi-JQ <yujinqi2@huawei.com>
Co-authored-by: zzhxx <2783294813@qq.com>
### What this PR does / why we need it?
move quant before allgather in Allgather EP, rely on
https://github.com/vllm-project/vllm-ascend/pull/3334
Deepseek R1 W8A8 performance on A2 with
`HCCL_ALGO="level0:NA;level1:pipeline"`:
| Seq length | Mean TTFT (ms) main | Mean TTFT (ms) this PR |
|----------|----------|----------|
| 4k | 375.21 | 364.99 |
| 16k | 1465.23 | 1421.75 |
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.11.0
- vLLM main:
83f478bb19
---------
Signed-off-by: realliujiaxu <realliujiaxu@163.com>
### What this PR does / why we need it?
1. Rename common_fused_moe.py to fused_moe.py.
2. Rename fused_moe_prepare_and_finalize.py / FusedMoEPrepareAndFinalize
to prepare_finalize.py / PrepareAndFinalize.
3. Rename vllm_ascend/ops/moe to vllm_ascend/ops/fused_moe.
4. Move vllm_ascend/ops/fused_moe.py to
vllm_ascend/ops/fused_moe/fused_moe.py
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
e2e & ut
- vLLM version: v0.11.0rc3
- vLLM main:
17c540a993
Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
Resolves a `TypeError: got an unexpected keyword argument 'layer_type'`.
A recent change (PR #3311) started passing the `layer_type` argument
when calling `get_pergroup_param()`. This specific implementation does
not use this parameter, causing the error.
This patch adds `layer_type=None` to the method signature to maintain
API compatibility and ignore the unused argument.
- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0
Signed-off-by: SlightwindSec <slightwindsec@gmail.com>
### What this PR does / why we need it?
1. Replace manual memory cleanup with passing parameter.
2. FusedMoEPrepareAndFinalizeWithMC2 inherits All2All avoid duplicated
code.
3. Fix MC2 bug introduced in
https://github.com/vllm-project/vllm-ascend/pull/3365
4. Unify aclgraph & eager in W8A8_dynamic.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
e2e & ut
- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0
Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
### What this PR does / why we need it?
**Problem Description:**
The existing implementation for the w4a8-dynamic linear method only
supports the old quantization format from msmodelslim. When attempting
to load models quantized with the new version, vLLM encounters errors
due to mismatched tensor shapes and unprocessed quantization parameters.
Relavant issues:
- https://github.com/vllm-project/vllm-ascend/issues/3192
- https://github.com/vllm-project/vllm-ascend/issues/3152
**Proposed Changes:**
1. Add support for w4a8 dynamic(new format) in
AscendW4A8DynamicLinearMethod and TorchairAscendW4A8DynamicLinearMethod
2. Add unit tests and e2e tests for w4a8 dynamic new and old format
models
<details>
<summary><b>details</b></summary>
1. **Support for new w4a8-dynamic format:**
* Detects quantization format by reading the "version" field in
quant_description to ensure backward compatibility.
* Handles the new pre-packed weight format (`2x int4` in an `int8`),
which has a halved dimension. It tells the vLLM loader how to unpack it
using `_packed_dim` and `_packed_factor`.
* Supports the new `scale_bias` parameter, setting its shape based on
the layer type, as required by msmodelslim. For api consistency and
future use, the `layer_type` parameter was also added to other
quantization methods.
* Updates the weight processing logic: new format weights are handled
with `.view(torch.int32)` since they're pre-packed, while old ones are
processed with `npu_convert_weight_to_int4pack`.
2. **New unit and E2E tests:**
* Added unit tests that verify the logic for both the old and new
formats.
* Split the distributed E2E test to confirm that both old and new format
models work correctly.
</details>
Theoretically, these changes will provide support for all common new
version w4a8(dynamic) models from msmodelslim.
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
I implement relevant unit tests and e2e tests and test the changes with
following commands:
```bash
# unit tests
python -m pytest tests/ut/quantization/test_w4a8_dynamic.py tests/ut/torchair/quantization/test_torchair_w4a8_dynamic.py -v
# e2e tests
pytest tests/e2e/singlecard/test_quantization.py -v -s
pytest tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_Qwen3_W4A8DYNAMIC_new_version -v -s
pytest tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_Qwen3_W4A8DYNAMIC_old_version -v -s
pytest tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_W4A8DYNAMIC -v -s
```
I also tested Hunyuan-1.8B-Instruct quantized with the new w4a8-dynamic
format:
```
vllm serve ./models/Hunyuan-1.8B-Instruct-quantized --gpu-memory-utilization 0.96 --quantization ascend --max-model-len 9600 --seed 0 --max-num-batched-tokens 16384
```
All tests mentioned passed locally.
**NOTE: I use quantization model from my own repo in
test_offline_inference_distributed.py**. Here is the description:
[Anionex/Qwen3-1.7B-W4A8-V1](https://modelscope.cn/models/Anionex/Qwen3-1.7B-W4A8-V1/summary)
(including quantization steps).This should be replaced by a model in
vllm-ascend ci modelscope repo.
Thanks for reading!
- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0
---------
Signed-off-by: Anionex <1005128408@qq.com>
This PR deletes model codes of deepseek_v2 and deepseek_v3 to reuse the
model file from vLLM.
vLLM Ascend now uses custom ops register way instead of model file
hard-coding.
- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0
---------
Signed-off-by: whx-sjtu <2952154980@qq.com>
This PR adds support for redundant experts in the EPLB.
Key points:
- Use global_num_experts = num_experts + num_redundant_experts
consistently.
- Backward compatible when num_redundant_experts=0.
Tested
On a 16-rank setup (W8A8) with static EPLB and expert_map_path,
verifying router logits shape and successful requests.
- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0
Signed-off-by: yechao237 <yechao20180411@gmail.com>
### What this PR does / why we need it?
This PR fixes issues:
1. Solve the problem that multimodal scene cannot do weight prefetching
and throw an assertion error exception.
2. Standardize the grid_thw data type of qwen2VL to torch.int32.
### Does this PR introduce _any_ user-facing change?
None.
### How was this patch tested?
- ci & e2e
- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0
---------
Signed-off-by: elilzhu <2435754260@qq.com>
Co-authored-by: zhulei (AK) <z00692222@china.huawei.com>
### What this PR does / why we need it?
Adapt deepseek-v3.2 to vllm 0.11.0, removing the useless patch.
The final goal is to remove all the patches and align the code arch to
vllm, thus we need to do the following work in next prs.
TODO:
- [x] remove patch on attention spec
- [ ] refactor the kvcache creation logic
### Does this PR introduce _any_ user-facing change?
N/A
### How was this patch tested?
1. CI passed with existing test.
2. Test pass with deepseek-v3.2-exp
- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0
Signed-off-by: MengqingCao <cmq0113@163.com>
What this PR does / why we need it?
1.Record expert map without dynamic eplb.
2.Add export PYTHONOPTIMIZE=1 when using dynamic eplb.
3.change eplb doc
Does this PR introduce any user-facing change?
How was this patch tested?
Qwen3_moe in A3.
- vLLM version: v0.11.0
---------
Signed-off-by: offline0806 <3337230449@qq.com>
Co-authored-by: offline0806 <3337230449@qq.com>
### What this PR does / why we need it?
The `row_idx` parameter is no longer used since
PR[#2689](https://github.com/vllm-project/vllm-ascend/pull/2689), so
remove it across multiple files to remove unnecessary calculations and
parameter passing.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
accuracy test passed for Qwen3 235B and DeepSeek V3 671B after this PR.
- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0
---------
Signed-off-by: CaranLic <740821011@qq.com>
### What this PR does / why we need it?
Currently, when executing to the Linear layer of models in vLLM-Ascend,
the weights format is ND in unquantized case and skipped ascend case.
This PR supplements the execution logic for Linear layer. We use a new
global variable: VLLM_ASCEND_ENABLE_NZ. When VLLM_ASCEND_ENABLE_NZ=1 and
CANN version is 8.3, the weights of the Linear layer will be converted
to FRACTAL_NZ, in both unquantized case and skipped ascend case. We also
use VLLM_ASCEND_ENABLE_NZ to control the existing NZ conversion, such as
w8a8-quantized case.
### Does this PR introduce _any_ user-facing change?
Add a new global variable VLLM_ASCEND_ENABLE_NZ. If you want to use NZ
format, you should set VLLM_ASCEND_ENABLE_NZ=1.
### 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: anon189Ty <Stari_Falcon@outlook.com>
### What this PR does / why we need it?
This PR fixes issues:
1. Resolve the issue of qwen2.5-VL quantization service startup failure:
AttributeError, 'Parameter' object has no attribute 'weight_loader'.
### Does this PR introduce _any_ user-facing change?
None.
### How was this patch tested?
- ci & e2e
- vLLM version: v0.11.0
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0
Signed-off-by: elilzhu <2435754260@qq.com>
### What this PR does / why we need it?
When using dynamic eplb,it will be blocking by nz tensor.We fix these
prolems by clone src tensor and recv tensor.
### Does this PR introduce any user-facing change?
### How was this patch tested?
Qwen3_moe in A3.
- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0
---------
Signed-off-by: offline0806 <3337230449@qq.com>
Co-authored-by: offline0806 <3337230449@qq.com>
### What this PR does / why we need it?
Due to the special input data during the dummy run, the majority of
tokens are distributed on DP0TP0, which results in insufficient
available KV cache on DP0TP0.
This PR changes the `topk_ids` of the dummy_run input from all zeros to
random values.
This is a naive implementation for experts load balance so as to avoid
accumulating too much tokens on a single rank.
### How was this patch tested?
model: DeepSeek-v3-w8a8
```bash
vllm serve DeepSeek-v3-w8a8 \
--host 0.0.0.0 \
--port 8004 \
--data-parallel-size 2 \
--tensor-parallel-size 8 \
--quantization ascend \
--seed 1024 \
--enforce-eager \
--served-model-name deepseek_v3 \
--enable-expert-parallel \
--disable-log-stats \
--max-num-seqs 18 \
--max-model-len 8192 \
--max-num-batched-tokens 8192 \
--trust-remote-code \
--no-enable-prefix-caching \
--gpu-memory-utilization 0.9 \
--speculative-config '{"num_speculative_tokens": 1, "method":"deepseek_mtp"}' \
--additional-config \
'{"ascend_scheduler_config":{"enabled":false},"torchair_graph_config":{"enabled":false}}'
```
The Available memory: **2728672256** -> **6771544064**
KV Cache size: **38144** -> **95232** tokens
After enabling load balance
- vLLM version: v0.11.0
---------
Signed-off-by: chenmenglong <chenmenglong1@huawei.com>
### What this PR does / why we need it?
- Refacotr and integrate a unified `WeightPrefetchMethod`
- Integrate `qkv_proj.weight` and `o_proj.weight` in quantized Attention
modules
- Prefetching these weights ahead of matmul-like operators imporves
performance by reducing L2 cache transfer latency
### Does this PR introduce _any_ user-facing change?
Add a new config in `--additional-config` for configuration:
```json
{
"weight_prefetch_config": {
"enabled": false,
"prefetch_ratio": {
"attn": {
"qkv": 1.0,
"o": 1.0,
},
},
},
}
```
This feature is enabled by default, and can be disabled through this
configuration
### How was this patch tested?
- vLLM version: v0.11.0
---------
Signed-off-by: yuzhup <15705211260@163.com>
Signed-off-by: zhoux77899 <zhouxiang100@huawei.com>
Co-authored-by: yuzhup <15705211260@163.com>
### What this PR does / why we need it?
1. Move additional functionalities from fused_moe.py to
common_fused_moe.py and remove fused_moe.py
2. Remove unnecessary custom classes from qwen3_moe.py, and it will be
completely removed after we release vllm-ascend v0.11.0
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
Qwen3-30B-A3B/Qwen3-30B-A3B-W8A8/DeepSeek-V3-W4A8-Pruing/deepseek-mtp/pangu-pro-moe-pruing:
1. Enable/Disable EP
3. Aclgraph & eager
4. SP
- vLLM version: v0.11.0
---------
Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
Co-authored-by: weijinqian0 <12153182+weijinqian0@users.noreply.github.com>
### What this PR does / why we need it?
1.Support deepseek w4a8 per-channel quantization
2.The eager mode supports converting weights to the NZ format
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
#### How to get weights using Modelslim
##### Installation steps
git clone https://gitcode.com/Ascend/msit.git
cd msit/msmodelslim
bash install.sh
##### Generate w4a8 per-channel weights
cd /example/DeepSeek
Command reference: msmodelslim/example/DeepSeek/README.md
- vLLM version: v0.10.2
- vLLM main:
f225ea7dd9
---------
Signed-off-by: Wang Kunpeng <1289706727@qq.com>
### What this PR does / why we need it?
Upgrade vLLM to newest commit
- Fix the aclgraph doesn't work problem, caused by
24fab45d96
- Fix PoolerOutput import error, caused by
755ed7b05b
- Fix the aclgraph weight load error to keep the same with torchair fix.
4492e3a554
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
All test should pass
- vLLM version: v0.10.2
- vLLM main:
52d0cb8458
---------
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
Some custom models in vllm-ascend define packed_modules_mapping, which
prevent keeping same model class with vllm community. So move these
custom packed_modules_mapping to quant utils.py. After this pr, some
custom models can be removed.
### Does this PR introduce _any_ user-facing change?
tested by CI
### How was this patch tested?
tested by CI
- vLLM version: v0.10.2
- vLLM main:
5089fd749c
Signed-off-by: 22dimensions <waitingwind@foxmail.com>
### Motivation
Currently dynamically experts balancing would stop-the-world.
Asynchronously expert load balancing would be better without flowing
problems:
Host-bound latency:
There are many cpu operations during EPLB such as
eplb-algorithm、creating p2p ops、and log2phy expert converting would
spend long cpu time, as ~1s.
Communication latency: The transfer time would cost much in the
situation without nvlink. As the weight of an expert maybe transfer to
multiple new positions, thus N times send/recv for one expert, with
result long latency. We had tested that batch_isend_irecv cost more
100ms for 16 experts weight transmission in A2 server of ascend.
SwiftBalancer would not stop-the-world anymore, in out test on NPU 1~2ms
cost for each layer while benefit 5ms-8ms decode latency with ep_size =
64.
The following updates have been made:
1、expert distribution recording with lower cost.
2、async cpu computing for eplb algo and other python operator.
3、new eplb algo with less expert rebalancing while almost the same
effect.
### Proposed Change
We will gradually migrate the EPLB logic to the VLLM community and
implement a generalized design. Relevant RFC:
https://github.com/vllm-project/vllm/issues/22246
The overall workflow involves:
<img width="801" height="302"
alt="474430541-23b06f58-23bc-44a3-a1be-00f268aeb15c"
src="https://github.com/user-attachments/assets/1d73a459-1b23-4b0a-812a-bf0a75debfed"
/>
1. Record experts distribution during forward. We using expert_token_num
after disptach instead of topk_ids, thus we got much smaller tensor
shape to reduce cost of hbm recording and add-operator.
2. Do all-gather for experts distribution. Using all-gather instead of
all-reduce as less traffic volume.
3. Wake up eplb worker process with experts distribution when
num_iterations comes. Run eplb algorithm in eplb worker.
4. Generate p2p send/recv ops and other operator such as log2phy would
cost long cpu time.
5. Lanch ibatch_send_recv in async_stream before forward.
6. After forward, wait for the ibatch_send_recv finish, then do uapte
expert map and expert weights.
### Co-author
Co-authored-by: raindaywhu raindaywhu@raindaywhu@ 163.con
Co-authored-by: njuyuan yuanjl19@smail.nju.edu.cn
Co-authored-by: qmkakaxi wjh1594260677@qq.com
Co-authored-by: Skywalker-EP 173723846@qq.com
- vLLM version: v0.10.2
- vLLM main:
567939953b
---------
Signed-off-by: offline0806 <z00858301@china.huawei.com>
Co-authored-by: offline0806 <z00858301@china.huawei.com>
### What this PR does / why we need it?
1. Replace prepare/finalize operation in fused_moe.py by
moe_comm_method.prepare()/finalize()
2. Replace unified_fused_experts by moe_comm_method.fused_experts() in
fused_moe.py/w8a8_dynamic.py/w4a8_dynamic.py
3. Add calling _select_moe_comm_method in spec-decode proposers.
4. Currently, w4a8_dynamic does not support gatherep, use all2allv
instead.
5. Remove redundant code.
### Does this PR introduce _any_ user-facing change?
AllgatherEP switch is disabled in aclgraph/eager mode, just follow the
rules in modelrunner_v1._select_moe_comm_method()
### How was this patch tested?
e2e & ut
- vLLM version: v0.10.2
- vLLM main:
7f6f2c1182
Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
Co-authored-by: weijinqian0 <12153182+weijinqian0@users.noreply.github.com>
### What this PR does / why we need it?
modelslim will generate self.bias for rms norm in quantization, since
RMSNorm in vllm has no this parameter, so its nesscesary
to create a AscendQuantRmsNorm.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
tested by deepseek-v3.1-w8a8
<img width="2496" height="592" alt="image"
src="https://github.com/user-attachments/assets/004c6e76-3d7a-4a1f-b59f-a14304012663"
/>
- vLLM version: main
- vLLM main:
d6249d0699
Signed-off-by: 22dimensions <waitingwind@foxmail.com>
### What this PR does / why we need it?
This PR sets the default format of GMM w2_weight in w8a8_dynamic to be
NZ to improve performance.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
- vLLM version: main
- vLLM main:
e40827280b
---------
Signed-off-by: Angazenn <supperccell@163.com>
### What this PR does / why we need it?
support qwen25 vl w8a8 quantization
### Does this PR introduce _any_ user-facing change?
N/A
### How was this patch tested?
- vLLM version: v0.10.1.1
- vLLM main:
62f66be1f7
---------
Signed-off-by: lijiaojiao <lijiaojiao990304@163.com>
Co-authored-by: lijiaojiao <lijiaojiao990304@163.com>
### What this PR does / why we need it?
Currently, when executing to the Linear layer of the model in
vLLM-Ascend, the weights input format is ND in unquantized case and
skipped ascend case, which is slower than FRACTAL_NZ.
This PR supplements the execution logic for Linear layer. When
VLLM_ASCEND_ENABLE_MLP_OPTIMIZE=1 and CANN version is 8.3, the weights
of the Linear layer will be converted to FRACTAL_NZ, in both unquantized
case and skipped ascend case.
- vLLM version: main
- vLLM main:
267c80d31f
Signed-off-by: anon189Ty <Stari_Falcon@outlook.com>
### What this PR does / why we need it?
1. Move prepare/finalize operation from moe_comm_method to
/ops/moe/fused_moe_prepare_and_finalize
2. Adapt to token_dispatcher in moe_comm_method
3. Move
moe_comm_method/experts_selector/token_dispatcher/fused_moe_prepare_and_finalize
to /ops/moe
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
e2e & ut
- vLLM version: v0.10.1.1
- vLLM main:
f4962a6d55
Signed-off-by: weichen <calvin_zhu0210@outlook.com>
Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
Co-authored-by: weijinqian0 <12153182+weijinqian0@users.noreply.github.com>
