### What this PR does / why we need it?
Qwen3 MoE supports SP. In scenarios like AlltoAll, AlltoAllv, and MC2,
replacing AllReduce with Reduce-Scatter and AllGather achieves
computational benefits in norm operations while saving one AllGather
communication. This feature is enabled during the P-phase and delivers
notable gains in long-sequence scenarios (e.g., 16k–25k), with
performance improvements reaching 5%–10%.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
```
compilation_config={
"pass_config":{
"enable_sequence_parallelism": True
}
},
enable_expert_parallel=True,
```
- vLLM version: v0.10.0
- vLLM main:
9edd1db02b
---------
Signed-off-by: libaokui <libaokui@huawei.com>
Co-authored-by: libaokui <libaokui@huawei.com>
### What this PR does / why we need it?
Fix `ascend_env has no attr VLLM_ASCEND_ENABLE_CHUNK_MC2`, remove
useless lines
- vLLM version: v0.10.0
- vLLM main:
9edd1db02b
---------
Signed-off-by: wangli <wangli858794774@gmail.com>
### What this PR does / why we need it?
Support MTP with：
- [x] V0 Scheduler
- [x] TorchAir
- [x] Single DP
- [x] Multi DP
- [x] Disaggregate PD
Known issues：
- [ ] Not support V1 Scheduler (chunked prefill), will be supported in a
few weeks
- [ ] vllm v0.10.0 does not support metrics with `DP > 1` right now,
need to comment out the line 171-175 in file
`vllm/vllm/v1/metrics/loggers.py`
```
if (len(self.engine_indexes) > 1
and vllm_config.speculative_config is not None):
raise NotImplementedError("Prometheus metrics with Spec Decoding "
"with >1 EngineCore per AsyncLLM is not "
"supported yet.")
```
To start an online server with torchair enabled, here is an example:
```
python -m vllm.entrypoints.openai.api_server \
--model="/weights/DeepSeek-R1_w8a8/" \
--trust-remote-code \
--max-model-len 40000 \
--tensor-parallel-size 4 \
--data_parallel_size 4 \
--max-num-seqs 16 \
--no-enable-prefix-caching \
--enable_expert_parallel \
--served-model-name deepseekr1 \
--speculative-config '{"num_speculative_tokens": 1, "method":"deepseek_mtp"}' \
--quantization ascend \
--host 0.0.0.0 \
--port 1234 \
--additional-config '{"ascend_scheduler_config":{"enabled":true,"enable_chunked_prefill":false},"torchair_graph_config":{"enabled":true,"graph_batch_sizes":[16]},"enable_weight_nz_layout":true}' \
--gpu_memory_utilization 0.9
```
offline example with torchair enabled
```
from vllm import LLM, SamplingParams
prompts = [
"Hello, my name is",
"The president of the United States is",
"The capital of France is",
"The future of AI is",
]
# Create a sampling params object.
sampling_params = SamplingParams(max_tokens=16, temperature=0)
# Create an LLM.
llm = LLM(
model="/home/data/DeepSeek-R1_w8a8/",
tensor_parallel_size=16,
max_num_seqs=16,
gpu_memory_utilization=0.9,
distributed_executor_backend="mp",
enable_expert_parallel=True,
speculative_config={
"method": "deepseek_mtp",
"num_speculative_tokens": 1,
},
trust_remote_code=True,
enforce_eager=False,
max_model_len=2000,
additional_config = {
'torchair_graph_config': {
'enabled': True,
"graph_batch_sizes": [16],
'enable_multistream_shared_expert': False,
},
"ascend_scheduler_config": {
"enabled": True
},
# 'expert_tensor_parallel_size': 16,
}
)
# Generate texts from the prompts.
# llm.start_profile()
outputs = llm.generate(prompts, sampling_params)
# llm.stop_profile()
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
```
- vLLM version: v0.10.0
- vLLM main:
302962e806
---------
Signed-off-by: xuyexiong <xuyexiong@huawei.com>
Before refactoring cross-DP decoding metadata aggregation, clean up the
token‐padding logic .
### What this PR does：
1. First checks whether any DP instance is in the prefill phase.
2. If in the `decode` phase and `torchair_graph_enabled `is true, pads
each DP instance’s token count up to the global maximum.
3. If in the `prefill` phase, or in decode phase with graph mode
**disabled**, returns each DP instance’s original token count without
padding.
This reordering removes the previous two‐step padding/unpadding flow and
ensures padding only occurs when strictly necessary.
- vLLM version: v0.10.0
- vLLM main:
bd3db7f469
Signed-off-by: yx0716 <jinyx1007@foxmail.com>
Signed-off-by: MengqingCao <cmq0113@163.com>
### What this PR does / why we need it?
This pr fix broken CI:
1. Fix the
ee2eb6ecd8
changes, in this commit, they fused the gate and up projections in the
vision MLP, This can improve performance by reducing one matrix
multiplication. so, this pr do the following things:
- Specify that the two linear layers are fused as `mlp.gate_up_proj`
when loading the weights.
- Use a SiluAndMul activation function.
2. Fix
aefeea0fde,
Update ModelRunnerOutput parameters to adapt to its changes
3. Fix
[vllm-commit](https://github.com/vllm-project/vllm/pull/20815/files#diff-3ffb829a39ab2b3e4706aa28f5e476815f36c3a87b98d6a66514ebedc8f3ffb4R354-R356),
fix qwen moe
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.10.0
- vLLM main:
fed5849d3f
---------
Signed-off-by: wangli <wangli858794774@gmail.com>
### What this PR does / why we need it?
We notice that vllm's main branch merged the PR
https://github.com/vllm-project/vllm/pull/21072 and
https://github.com/vllm-project/vllm/pull/21473 to support ray backend
and fix some rebase bug from previous change. Those changes makes the
disaggregate pd in vllm ascend breaks in some scenario.
In this PR, we adopt those changes to make sure the
`llmdatddist_c_mgr_connector` works fine on the newest vllm main branch.
### Does this PR introduce _any_ user-facing change?
No user face change.
### How was this patch tested?
relevant ut will be added to make sure the functionality of those
changes.
- vLLM version: v0.10.0
- vLLM main:
ad57f23f6a
---------
Signed-off-by: ganyi <pleaplusone.gy@gmail.com>
### What this PR does / why we need it?
Cherry pick #1291 from v0.9.1-dev, This pr implement the synchronization
of whether `dbo` is enabled across all dp ranks. specifically, it
performed allreduce op across multiple DP ranks, only when all the dp
rank is `enable_dbo`, it is enabled
Co-authored-by: shikang-hangzhou <459956190@qq.com>
Co-authored-by: wangli <wangli858794774@gmail.com>
- vLLM version: v0.10.0
- vLLM main:
2836dd73f1
---------
Signed-off-by: wangli <wangli858794774@gmail.com>
### What this PR does / why we need it?
Fix#2033
Sync https://github.com/vllm-project/vllm/pull/14702 to solve
`grammar_bitmask` IndexError caused by outdated `apply_grammar_bitmask`
method
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
Tested by upstream vllm
- vLLM version: v0.10.0
- vLLM main:
6e599eebe8
Signed-off-by: ApsarasX <apsarax@outlook.com>
Refactor Sampler implementation from patch way to inherit from vLLM
Sampler interface.
Next step: Make the op `TopKTopPSampler` in vLLM support custom ops
register mechanism
- vLLM version: v0.10.0
- vLLM main:
61a6905ab0
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Clean up useless import from vllm to make code more clear.
- vLLM version: v0.10.0
- vLLM main:
18cc33dd60
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
A refactoring of forward_context and model_runner_v1, add some context
which is necessary in model inference into forward_context, and refactor
dummy_run logic, make it more reasonable.
Some details for this PR:
Add `ascend_forward_context`;
Update mc2_v2 op, and support `active_mask` param;
Update scripts in examples dir;
refactor `dummy_run` logic;
Add soc_version for A2 and A3;
### Does this PR introduce _any_ user-facing change?
No change at user-facing.
### How was this patch tested?
- vLLM version: v0.10.0
- vLLM main:
57c22e57f9
Signed-off-by: zzzzwwjj <1183291235@qq.com>
### What this PR does / why we need it?
- Upgrade to v0.10.0
- Drop v0.9.2 version compatibility
- Add patch for
`vllm_ascend/patch/worker/patch_common/patch_sampler_gather_logprobs.py`
as workaround of
f3a683b7c9
for v0.10.0 and also add e2e test `test_models_prompt_logprobs`
- Pin transformers<4.54.0 as workaround of
https://github.com/vllm-project/vllm-ascend/issues/2034
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
- Test locally:
`VLLM_USE_MODELSCOPE=true pytest -sv
tests/e2e/singlecard/test_offline_inference.py::test_models_prompt_logprobs`
- CI passed
- vLLM version: v0.9.2
- vLLM main:
7728dd77bb
---------
Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
Before do attention module refactor, we can do some code cleanup to make
the next step easier.
What this PR does:
1. remove uesless `common_prefix_len` for attention builder
2. remove uesless `is_only_prefill` and `num_input_tokens` in attention
metadata.
3. remove `CommonAttentionMetadata` and ues `query_start_loc` instead,
`CommonAttentionMetadata` is over designed and uesless
4. update the attention backend input parameters to keep the same as
vLLM.
5. Rename attention name to the same style with `ASCEND` prefix
- vLLM version: v0.9.2
- vLLM main:
107111a859
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
Support pipeline parallel with ray backend in V1Engine.
Fixes#1751
### Does this PR introduce _any_ user-facing change?
Users could specify ray as distributed backend when inferencing with pp
### How was this patch tested?
CI passed with new added test.
- vLLM version: v0.9.2
- vLLM main:
32142b3c62
---------
Signed-off-by: MengqingCao <cmq0113@163.com>
There is a lot torchair specified logic in common code. It results hard
code maintenance. We will create a new torchair module to launch
torchair related logic there. I plan to add 4 PR.
1. Refactor worker
2. Refactor utils (this PR)
- simple change that move all torchair related util function to torchair
module
3. Refactor model_runner
4. Refactor attention
- vLLM version: v0.9.2
- vLLM main:
8188196a1c
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
1. vLLM commit
45badd05d0
changed the pooling check logic which broken vLLM Ascend.
2. vLLM commit
3e04107d97
requires higher version of transformers. The transformers version bug
has been fixed by
e936e401de.
We can safe to remove the version limit now.
3. vLLM commit
217937221b
added a new input `enable_eplb` for FusedMoe Ops
This PR fix the broken CI.
- vLLM version: v0.9.2
- vLLM main:
6a971ed692
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
This patch supports pipeline parallel in V1 Engine
### Does this PR introduce _any_ user-facing change?
Yes, users can run PP in V1
### How was this patch tested?
Manully test
- vLLM version: v0.9.2
- vLLM main:
31d5c1797f
Signed-off-by: weiguihua2 <weiguihua2@huawei.com>
### What this PR does / why we need it?
Follow vllm-project/vllm lint way:
https://github.com/vllm-project/vllm/blob/main/.pre-commit-config.yaml
Enable pre-commit to avoid some low level error AMAP.
This pr is one step of #1241, The purpose is make linting system more
clear and convenient, on this step, Mainly did the following things:
yapf, actionlint, ruff, typos, isort, mypy, png-lint, signoff-commit,
enforce-import-regex-instead-of-re.
TODO:
- clang-format(check for csrc with google style)
need clean code, disable for now
- pymarkdown
need clean code, disable for now
- shellcheck
need clean code, disable for now
### Does this PR introduce _any_ user-facing change?
Only developer UX change:
https://vllm-ascend--1256.org.readthedocs.build/en/1256/developer_guide/contributing.html#run-lint-locally
```
pip install -r requirements-lint.txt && pre-commit install
bash format.sh
```
### How was this patch tested?
CI passed with new added/existing test.
Co-authored-by: Yikun [yikunkero@gmail.com](mailto:yikunkero@gmail.com)
Co-authored-by: wangli
[wangli858794774@gmail.com](mailto:wangli858794774@gmail.com)
- vLLM version: v0.9.1
- vLLM main:
5358cce5ff
---------
Signed-off-by: wangli <wangli858794774@gmail.com>
vllm has released 0.9.2. This PR drop 0.9.1 support.
- vLLM version: v0.9.1
- vLLM main:
b942c094e3
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
1、Sometimes loading torchair cache will fail because of the floating of
npu memory, so this pr add a new cache to save the old kv cache bytes to
avoid the possible crash while loading the torchair graph cache.
2、When caching is enabled and does not exist, the first compilation
introduces the overhead of Dynamo Gurad. So in this case, we will
compile them directly twice to skip them (This will bring 3-4 ms of tpot
optimization)
### Does this PR introduce _any_ user-facing change?
Add a new env `VLLM_ASCEND_KV_CACHE_MEGABYTES_FLOATING_TOLERANCE` to
control kv cache floating tolerance
### How was this patch tested?
- vLLM version: v0.9.1
- vLLM main:
1fd471e957
Signed-off-by: boying <897013703@qq.com>
### What this PR does / why we need it?
Since running on Altlas 300I Duo was initial supported after #1333 ,
this PR will disable the JIT compiler for the 310P and changed the data
format to NZ for the weight in the vocabulary embedding and QKV
projection layers, which help improving performance.
See #1563
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
Test manually:
https://github.com/vllm-project/vllm-ascend/pull/1591#issuecomment-3028352339
Signed-off-by: Vincent Yuan <farawayboat@gmail.com>
### What this PR does / why we need it?
This PR supports torchair graph mode with non-mla backend on both 800IA2
and 300I Duo platforms. The main change is to add
`attention_v1_torchair.py` to support specific attention related
operations that are required by torchair.
### Does this PR introduce _any_ user-facing change?
Before this PR, vLLM-Ascend only allows deepseek to use torchair. Now we
can also use it with pangu. Besides, we add a support model list to
control which type of models that can use torchair.
### How was this patch tested?
We have test it with PanguProMoE on both 800IA2 and 300I Duo platforms,
and model generates answer normally.
---------
Signed-off-by: angazenn <zengyanjia@huawei.com>
Signed-off-by: tianyitang <tangtianyi4@huawei.com>
Co-authored-by: angazenn <zengyanjia@huawei.com>
Co-authored-by: tianyitang <tangtianyi4@huawei.com>
### What this PR does / why we need it?
This pr supports w8a8 on 300I Duo platform. The main change is to use
`npu_quant_grouped_matmul_dequant` to replace `npu_grouped_matmul`.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
offline inference on 310p runs normally.
---------
Signed-off-by: angazenn <zengyanjia@huawei.com>
Signed-off-by: tianyitang <tangtianyi4@huawei.com>
Co-authored-by: angazenn <zengyanjia@huawei.com>
Co-authored-by: tianyitang <tangtianyi4@huawei.com>
### What this PR does / why we need it?
1. drop some useless code for w8a8 fusedmoe
2. Add in8 kv cache check
3. Add more ut.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
CI passed with new added test.
---------
Signed-off-by: zhuyilin <809721801@qq.com>
Signed-off-by: tianyitang <tangtianyi4@huawei.com>
Co-authored-by: tianyitang <tangtianyi4@huawei.com>
### What this PR does / why we need it?
This PR (adapted from
2863befce3)
updates the CachedRequestData definition to use a single instance shared
across all requests in a batch, instead of creating a new instance per
request.
Found ci boken by the vllm's model_runner change: `ERROR 07-01 09:53:53
[core.py:521] TypeError: 'CachedRequestData' object is not iterable`,
Modify the model_runner to fix it.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
pass ci will verify this.
---------
Signed-off-by: ganyi <pleaplusone.gy@gmail.com>
Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
Co-authored-by: Yikun Jiang <yikunkero@gmail.com>
### What this PR does / why we need it?
Change as little existing code as possible to add v1 pooling task's
support, notice that i move down the `vllm.v1.worker.gpu_input_batch` to
vllm-ascend, Considering the frequent changes in upstream interfaces, in
order to decouple, so i move it here
### How was this patch tested?
CI passed with new added/existing test, and I have a simple test was
first conducted locally which is adapted from
https://www.modelscope.cn/models/Qwen/Qwen3-Embedding-0.6B, just like
bellow：
```python
import os
import torch
from vllm import LLM
os.environ["VLLM_USE_MODELSCOPE"]="True"
def get_detailed_instruct(task_description: str, query: str) -> str:
return f'Instruct: {task_description}\nQuery:{query}'
# Each query must come with a one-sentence instruction that describes the task
task = 'Given a web search query, retrieve relevant passages that answer the query'
queries = [
get_detailed_instruct(task, 'What is the capital of China?'),
get_detailed_instruct(task, 'Explain gravity')
]
# No need to add instruction for retrieval documents
documents = [
"The capital of China is Beijing.",
"Gravity is a force that attracts two bodies towards each other. It gives weight to physical objects and is responsible for the movement of planets around the sun."
]
input_texts = queries + documents
model = LLM(model="Qwen/Qwen3-Embedding-0.6B", task="embed")
outputs = model.embed(input_texts)
embeddings = torch.tensor([o.outputs.embedding for o in outputs])
scores = (embeddings[:2] @ embeddings[2:].T)
print(scores.tolist())
# [[0.7620252966880798, 0.14078938961029053], [0.1358368694782257, 0.6013815999031067]]
```
---------
Signed-off-by: wangli <wangli858794774@gmail.com>
Signed-off-by: wangli <858794774@qq.com>
Co-authored-by: wangli <858794774@qq.com>
### What this PR does / why we need it?
support pangu moe w8a8c8
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
CI passed with new added test.
Signed-off-by: zhuyilin <809721801@qq.com>
### What this PR does / why we need it?
Support prompt logprobs in V1. This also enable lm_eval to test accuracy
on V1
### Does this PR introduce _any_ user-facing change?
support prompt logprobs output
### How was this patch tested?
CI passed with accuracy test.
Using lm_eval, which use prompt logprobs as output to test accuracy, to
test:
```python
VLLM_USE_V1=1 lm_eval \
--model vllm \
--model_args pretrained=Qwen/Qwen2.5-7B-Instruct,max_model_len=4096,block_size=4 \
--tasks ceval-valid_computer_network \
--batch_size 8
```
After this pr, the accuracy test results of `Qwen/Qwen2.5-7B-Instruct`
on V1 is:
```bash
| Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
|----------------------------|------:|------|-----:|--------|---|-----:|---|-----:|
|ceval-valid_computer_network| 2|none | 0|acc |↑ |0.7368|± |0.1038|
| | |none | 0|acc_norm|↑ |0.7368|± |0.1038|
```
Closes: https://github.com/vllm-project/vllm-ascend/issues/1043
Signed-off-by: MengqingCao <cmq0113@163.com>
### What this PR does / why we need it?
Reset all unused positions in `NPUModelRunner` to prevent out-of-bounds
asserts in the `GatherV3` operator.
Currently, in
[`get_splitfuse_attn_mask`](https://github.com/vllm-project/vllm-ascend/blob/main/vllm_ascend/attention/attention.py#L124),
the `position` tensor may contain values that exceed the dimensions of
the attention mask, triggering a `GatherV3` boundary check failure.
These invalid indices originate from stale “dirty” entries left over in
`position` due to padding logic in the ACL graph. Specifically, in
[`_process_reqs`](https://github.com/vllm-project/vllm-ascend/blob/main/vllm_ascend/worker/model_runner_v1.py#L989),
the variable `num_input_tokens` is always greater than or equal to
`total_num_scheduled_tokens`, so any positions not explicitly cleared
from a previous batch will persist and cause this sporadic error.
BTW, in the original vLLM implementation, masks are constructed
internally using other args, so these lingering values do not surface.
However, on the Ascend platform—where split-fuse attention requires
externally supplied masks—these residual indices become critical and
lead to this elusive, hard-to-reproduce failure.
The fix is to explicitly reset or zero out all unused entries in the
`position` tensor before passing it to `GatherV3`, ensuring that every
index lies within the valid range of the attention mask.
Closes: https://github.com/vllm-project/vllm-ascend/issues/1038
### Does this PR introduce _any_ user-facing change?
No
Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
This PR aims to clean up the useless code for LLM setup. It helps to
make the code more clear.
1. remove useless `self.xxx` property
2. change `set_random_seed` to `seed_everything`
3. remove `set_custom_all_reduce`, it's only used for cuda
This is just a code clean. no change for any code logic.
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
Sync MRotaryEmbedding interface change to recover main CI
(https://github.com/vllm-project/vllm/pull/19939)
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
CI passed
---------
Signed-off-by: wangli <wangli858794774@gmail.com>
### What this PR does / why we need it?
Add initial experimental support for Ascend 310P, this patch squash
below PR into one to help validation:
- https://github.com/vllm-project/vllm-ascend/pull/914
- https://github.com/vllm-project/vllm-ascend/pull/1318
- https://github.com/vllm-project/vllm-ascend/pull/1327
### Does this PR introduce _any_ user-facing change?
User can run vLLM on Altlas 300I DUO series
### How was this patch tested?
CI passed with:
- E2E image build for 310P
- CI test on A2 with e2e test and longterm test
- Unit test missing because need a real 310P image to have the test,
will add in a separate PR later.
- Manually e2e test:
- Qwen2.5-7b-instruct, Qwen2.5-0.5b, Qwen3-0.6B, Qwen3-4B, Qwen3-8B:
https://github.com/vllm-project/vllm-ascend/pull/914#issuecomment-2942989322
- Pangu MGoE 72B
The patch has been tested locally on Ascend 310P hardware to ensure that
the changes do not break existing functionality and that the new
features work as intended.
#### ENV information
CANN, NNAL version: 8.1.RC1
> [!IMPORTANT]
> PTA 2.5.1 version >= torch_npu-2.5.1.post1.dev20250528 to support NZ
format and calling NNAL operators on 310P
#### Code example
##### Build vllm-ascend from source code
```shell
# download source code as vllm-ascend
cd vllm-ascend
export SOC_VERSION=Ascend310P3
pip install -v -e .
cd ..
```
##### Run offline inference
```python
from vllm import LLM, SamplingParams
prompts = ["水的沸点是100摄氏度吗？请回答是或者否。", "若腋下体温为38摄氏度，请问这人是否发烧？请回答是或者否。",
"水的沸点是100摄氏度吗？请回答是或者否。", "若腋下体温为38摄氏度，请问这人是否发烧？请回答是或者否。"]
# Create a sampling params object.
sampling_params = SamplingParams(temperature=0.0, top_p=0.95, max_tokens=10)
# Create an LLM.
llm = LLM(
model="Qwen/Qwen2.5-7B-Instruct",
max_model_len=4096,
max_num_seqs=4,
dtype="float16", # IMPORTANT cause some ATB ops cannot support bf16 on 310P
disable_custom_all_reduce=True,
trust_remote_code=True,
tensor_parallel_size=2,
compilation_config={"custom_ops":['none', "+rms_norm", "+rotary_embedding"]},
)
# Generate texts from the prompts.
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}")
```
---------
Signed-off-by: Vincent Yuan <farawayboat@gmail.com>
Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
Signed-off-by: angazenn <zengyanjia@huawei.com>
Co-authored-by: Vincent Yuan <farawayboat@gmail.com>
Co-authored-by: angazenn <zengyanjia@huawei.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: shen-shanshan <467638484@qq.com>
### What this PR does / why we need it?
This PR implements the Eagle Pososer feature for vLLM v1, which enables
more efficient speculative decoding by using a draft model to predict
potential future tokens.
- The implementation includes the core Eagle algorithm integration with
vLLM's existing architecture, allowing for faster inference while
maintaining output quality.
- This is needed to significantly improve the generation speed of large
language models without compromising on the quality of generated text.
### Does this PR introduce any user-facing change?
Yes, this PR introduces a new speculative decoding mode that can be
enabled via configuration.
- Users can now choose to use Eagle Pososer by setting appropriate flags
in the inference configuration.
- The API remains backward compatible, with the new functionality being
opt-in.
### How was this patch tested?
CI passed with new unit tests added for the Eagle Pososer functionality.
- Benchmark tests were conducted comparing generation speed and quality
with and without Eagle Pososer.
- Integration tests were performed with various model architectures to
ensure compatibility.
- Manual testing was done using different prompt scenarios to verify
output quality remains consistent.
- we test accept rate on one Ascend 910B npu, The acceptance rate
results are basically consistent with those shown here:
https://github.com/vllm-project/vllm/pull/16937
- Currently, we support scenarios where num_spec_tokens <= 2. When
num_spec_tokens > 2, issues such as insufficient GPU memory and operator
computation errors may occur. We will address this in subsequent
updates.
- We will add support for Eagle v1 in future updates.
### Acceptance Test Script
```bash
SCRIPT="/offline/eagle.py"
DATASET="ShareGpt"
MODEL=Meta-Llama-3.1-8B-Instruct
DRAFT=EAGLE3-LLaMA3.1-Instruct-8B
CUDA_VISIBLE_DEVICES="0" VLLM_USE_V1=1 $PYTHON $SCRIPT \
--dataset $DATASET \
--num_spec_tokens 2 \
--max_num_seqs 1 \
--model_dir $MODEL \
--eagle_dir $DRAFT \
--tp 1 \
--num_prompts 80
```
### Acceptance Test Results
```bash
██████████████████████████████████████████████████████████████████████████████████████████████████████████| 80/80 [21:22<00:00, 16.03s/it, est. speed input: 4.72 toks/s, output: 13.56 toks/s]
-------------------------------------------------------------------------------------
mean acceptance length: 1.63
-------------------------------------------------------------------------------------
total_counts: 8062
acceptance at token 0: 1.00 (8062 times)
acceptance at token 1: 0.70 (5612 times)
acceptance at token 2: 0.47 (3765 times)
```
Closes: https://github.com/vllm-project/vllm-ascend/issues/1004
---------
Signed-off-by: yuancaoyaoHW <a2749322671@gmail.com>
<!-- Thanks for sending a pull request!
BEFORE SUBMITTING, PLEASE READ
https://docs.vllm.ai/en/latest/contributing/overview.html
-->
### What this PR does / why we need it?
This PR is used for resolved [issue
1147](https://github.com/vllm-project/vllm-ascend/issues/1147)
1. Move fused_moe code into one file `fused_moe.py`.
2. Integrate branch conditions into function `get_fused_moe_state`.
<!--
- Please clarify what changes you are proposing. The purpose of this
section is to outline the changes and how this PR fixes the issue.
If possible, please consider writing useful notes for better and faster
reviews in your PR.
- Please clarify why the changes are needed. For instance, the use case
and bug description.
- Fixes #
-->
### Does this PR introduce _any_ user-facing change?
1. This PR has removed the env `VLLM_ENABLE_MC2`, because I think this
env is useless, we can make judgments based on the current scenario
without this env, it will only increase complexity.
2. This PR has removed the env `USING_LCCL_COM`, because this env has
already expired.
3. `additional_config.expert_tensor_parallel_size` has already expired,
and now we also use parameter `enable_expert_parallel`, consistent with
the vLLM.
<!--
Note that it means *any* user-facing change including all aspects such
as API, interface or other behavior changes.
Documentation-only updates are not considered user-facing changes.
-->
### How was this patch tested?
<!--
CI passed with new added/existing test.
If it was tested in a way different from regular unit tests, please
clarify how you tested step by step, ideally copy and paste-able, so
that other reviewers can test and check, and descendants can verify in
the future.
If tests were not added, please describe why they were not added and/or
why it was difficult to add.
-->
Signed-off-by: zzzzwwjj <1183291235@qq.com>
1. upgrade vllm to 0.9.1. 0.9.0 is not supported for main branch now.
keep doc to 0.9.0 until we release the first 0.9.1 release.
2. disable V0 test for PR
3. move actionlint check to lint job
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
