e90b14140b
### What this PR does / why we need it?
This PR is to replace addRmsNorm and Add With addRmsNormBias. This way
can lead to a more effecient result.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
Full Test Pass
- vLLM version: v0.13.0
- vLLM main:
2f4e6548ef
Signed-off-by: Chen_HaoWen <chenhaowen12@huawei.com>
Co-authored-by: Chen_HaoWen <chenhaowen12@huawei.com>
80 lines
2.9 KiB
Python
80 lines
2.9 KiB
Python
#
|
|
# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
|
|
# Copyright 2023 The vLLM team.
|
|
#
|
|
# 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.
|
|
# This file is a part of the vllm-ascend project.
|
|
#
|
|
from modelscope import snapshot_download # type: ignore[import-untyped]
|
|
|
|
from tests.e2e.conftest import VllmRunner
|
|
from tests.e2e.model_utils import check_outputs_equal
|
|
|
|
|
|
def test_qwen3_w8a8_quant():
|
|
max_tokens = 5
|
|
example_prompts = [
|
|
"vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs."
|
|
]
|
|
vllm_target_outputs = [([
|
|
85, 4086, 44, 374, 264, 1550, 42747, 628, 323, 4938, 72816, 44378, 323,
|
|
13480, 4712, 369, 444, 10994, 82, 13, 1084, 374, 6188, 369, 3460
|
|
], 'vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. It is designed for large'
|
|
)]
|
|
|
|
with VllmRunner(
|
|
snapshot_download("vllm-ascend/Qwen3-0.6B-W8A8"),
|
|
max_model_len=8192,
|
|
gpu_memory_utilization=0.7,
|
|
cudagraph_capture_sizes=[1, 2, 4, 8],
|
|
quantization="ascend",
|
|
) as vllm_model:
|
|
vllm_quant_w8a8_outputs = vllm_model.generate_greedy(
|
|
example_prompts, max_tokens)
|
|
|
|
check_outputs_equal(
|
|
outputs_0_lst=vllm_target_outputs,
|
|
outputs_1_lst=vllm_quant_w8a8_outputs,
|
|
name_0="vllm_target_outputs",
|
|
name_1="vllm_quant_w8a8_outputs",
|
|
)
|
|
|
|
|
|
def test_qwen3_dense_w8a16():
|
|
max_tokens = 5
|
|
example_prompts = [
|
|
"vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs."
|
|
]
|
|
vllm_target_outputs = [([
|
|
85, 4086, 44, 374, 264, 1550, 42747, 628, 323, 4938, 72816, 44378, 323,
|
|
13480, 4712, 369, 444, 10994, 82, 13, 1084, 374, 6188, 311, 387
|
|
], 'vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. It is designed to be'
|
|
)]
|
|
|
|
with VllmRunner(
|
|
snapshot_download("vllm-ascend/Qwen3-0.6B-W8A16"),
|
|
max_model_len=8192,
|
|
enforce_eager=False,
|
|
gpu_memory_utilization=0.7,
|
|
quantization="ascend",
|
|
) as vllm_model:
|
|
vllm_quant_w8a16_outputs = vllm_model.generate_greedy(
|
|
example_prompts, max_tokens)
|
|
|
|
check_outputs_equal(
|
|
outputs_0_lst=vllm_target_outputs,
|
|
outputs_1_lst=vllm_quant_w8a16_outputs,
|
|
name_0="vllm_target_outputs",
|
|
name_1="vllm_quant_w8a16_outputs",
|
|
)
|