26fc36b0e0
### 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>
75 lines
3.0 KiB
Python
75 lines
3.0 KiB
Python
#
|
|
# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
|
|
# This file is a part of the vllm-ascend project.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
#
|
|
|
|
from typing import Tuple
|
|
|
|
import torch
|
|
from vllm.distributed import tensor_model_parallel_all_reduce
|
|
from vllm.model_executor.layers.vocab_parallel_embedding import \
|
|
VocabParallelEmbedding
|
|
|
|
|
|
def get_masked_input_and_mask(
|
|
input_: torch.Tensor, org_vocab_start_index: int,
|
|
org_vocab_end_index: int, num_org_vocab_padding: int,
|
|
added_vocab_start_index: int,
|
|
added_vocab_end_index: int) -> Tuple[torch.Tensor, torch.Tensor]:
|
|
# torch.compile will fuse all of the pointwise ops below
|
|
# into a single kernel, making it very fast
|
|
org_vocab_mask = (input_ >= org_vocab_start_index) & (
|
|
input_ < org_vocab_end_index)
|
|
# Adapt: avoid create added_vocab_mask when added_vocab_start_index == added_vocab_end_index.
|
|
if added_vocab_start_index == added_vocab_end_index:
|
|
valid_offset = (org_vocab_start_index * org_vocab_mask)
|
|
vocab_mask = org_vocab_mask
|
|
else:
|
|
added_vocab_mask = (input_ >= added_vocab_start_index) & (
|
|
input_ < added_vocab_end_index)
|
|
added_offset = added_vocab_start_index - (
|
|
org_vocab_end_index -
|
|
org_vocab_start_index) - num_org_vocab_padding
|
|
valid_offset = (org_vocab_start_index *
|
|
org_vocab_mask) + (added_offset * added_vocab_mask)
|
|
vocab_mask = org_vocab_mask | added_vocab_mask
|
|
# Adapt end.
|
|
input_ = vocab_mask * (input_ - valid_offset)
|
|
return input_, ~vocab_mask
|
|
|
|
|
|
def vocab_parallel_embedding_forward(self, input_):
|
|
if self.tp_size > 1:
|
|
# Build the mask.
|
|
masked_input, input_mask = get_masked_input_and_mask(
|
|
input_, self.shard_indices.org_vocab_start_index,
|
|
self.shard_indices.org_vocab_end_index,
|
|
self.shard_indices.num_org_vocab_padding,
|
|
self.shard_indices.added_vocab_start_index,
|
|
self.shard_indices.added_vocab_end_index)
|
|
else:
|
|
masked_input = input_
|
|
# Get the embeddings.
|
|
output_parallel = self.quant_method.embedding(self, masked_input.long())
|
|
# Mask the output embedding.
|
|
if self.tp_size > 1:
|
|
output_parallel.masked_fill_(input_mask.unsqueeze(-1), 0)
|
|
# Reduce across all the model parallel GPUs.
|
|
output = tensor_model_parallel_all_reduce(output_parallel)
|
|
return output
|
|
|
|
|
|
VocabParallelEmbedding.forward = vocab_parallel_embedding_forward
|