e564470338
### What this PR does / why we need it?
moe support for llama4 and mllama4 in vllm-ascend
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
start sever:
python -m vllm.entrypoints.openai.api_server --model
/data/nfs/benchmark/tokenizer/Llama-4-Scout-17B-16E-Instruct \
--max-num-seqs=256 \
--max-model-len=8192 \
--tensor-parallel-size=8 \
--block-size=128 \
--dtype bfloat16 \
--host=0.0.0.0 \
--port=8000 \
--gpu-memory-utilization=0.9 \
--trust-remote-code
client:
python online_server.py --model-path
/data/nfs/benchmark/tokenizer/Llama-4-Scout-17B-16E-Instruct
--image-path /data/nfs/w60040464/cherry_blossom.jpg --docker-ip
7.242.108.253 --served-port 8000 --text "what is the content of this
image?"
result:
{'id': 'chatcmpl-2b709a5d2e1a4017991ec4ba8248686a', 'object':
'chat.completion', 'created': 1747056823, 'model':
'/data/nfs/benchmark/tokenizer/Llama-4-Scout-17B-16E-Instruct',
'choices': [{'index': 0, 'message': {'role': 'assistant',
'reasoning_content': None, 'content': 'The image depicts a tower, likely
Tokyo Skytree, framed by branches of a cherry blossom tree. The tower is
white and has a distinctive shape, with a large sphere at the top and a
long, thin spire extending from it. The branches of the cherry blossom
tree are in the foreground, with pink flowers blooming on them. The
background is a clear blue sky.\n\n**Key Features:**\n\n* **Tower:**
White, spherical shape at the top, long thin spire\n', 'tool_calls':
[]}, 'logprobs': None, 'finish_reason': 'length', 'stop_reason': None}],
'usage': {'prompt_tokens': 2340, 'total_tokens': 2440,
'completion_tokens': 100, 'prompt_tokens_details': None},
'prompt_logprobs': None}
Signed-off-by: chenxu <chenxu68@huawei.com>
Co-authored-by: chenxu <chenxu68@huawei.com>
Co-authored-by: evian <eviantai@u.nus.edu>
70 lines
2.2 KiB
Python
70 lines
2.2 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 Callable, Optional
|
|
|
|
import torch
|
|
from vllm.model_executor.layers.fused_moe.layer import \
|
|
UnquantizedFusedMoEMethod
|
|
|
|
from vllm_ascend.ops.fused_moe import fused_experts, select_experts
|
|
|
|
|
|
def forward_oot(
|
|
self,
|
|
layer: torch.nn.Module,
|
|
x: torch.Tensor,
|
|
use_grouped_topk: bool,
|
|
top_k: int,
|
|
router_logits: torch.Tensor,
|
|
renormalize: bool,
|
|
topk_group: Optional[int] = None,
|
|
num_expert_group: Optional[int] = None,
|
|
custom_routing_function: Optional[Callable] = None,
|
|
scoring_func: str = "softmax",
|
|
e_score_correction_bias: Optional[torch.Tensor] = None,
|
|
global_num_experts: Optional[int] = None,
|
|
expert_map: Optional[torch.Tensor] = None,
|
|
apply_router_weight_on_input: bool = False,
|
|
activation: str = "silu",
|
|
) -> torch.Tensor:
|
|
topk_weights, topk_ids = select_experts(
|
|
hidden_states=x,
|
|
router_logits=router_logits,
|
|
top_k=top_k,
|
|
use_grouped_topk=use_grouped_topk,
|
|
renormalize=renormalize,
|
|
topk_group=topk_group,
|
|
num_expert_group=num_expert_group,
|
|
custom_routing_function=custom_routing_function,
|
|
scoring_func=scoring_func,
|
|
e_score_correction_bias=e_score_correction_bias,
|
|
)
|
|
|
|
return fused_experts(
|
|
hidden_states=x,
|
|
w1=layer.w13_weight,
|
|
w2=layer.w2_weight,
|
|
topk_weights=topk_weights,
|
|
topk_ids=topk_ids,
|
|
top_k=top_k,
|
|
expert_map=expert_map,
|
|
apply_router_weight_on_input=apply_router_weight_on_input)
|
|
|
|
|
|
UnquantizedFusedMoEMethod.forward_oot = forward_oot
|