Files
xc-llm-ascend/tests/ut/test_ascend_config.py

94 lines
3.5 KiB
Python
Raw Normal View History

#
# 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 vllm.config import VllmConfig
from tests.ut.base import TestBase
from vllm_ascend.ascend_config import (clear_ascend_config, get_ascend_config,
init_ascend_config)
class TestAscendConfig(TestBase):
@staticmethod
def _clean_up_ascend_config(func):
def wrapper(*args, **kwargs):
clear_ascend_config()
func(*args, **kwargs)
clear_ascend_config()
return wrapper
@_clean_up_ascend_config
def test_init_ascend_config_without_additional_config(self):
test_vllm_config = VllmConfig()
# No additional config given, check the default value here.
ascend_config = init_ascend_config(test_vllm_config)
self.assertIsNone(ascend_config.expert_map_path)
self.assertFalse(ascend_config.multistream_overlap_shared_expert)
Adopt inductor fusion and define quantization fusion pass (#4168) ### What this PR does / why we need it? The main goal of this PR to alleviate the high maintenance burden from model duplication when we are going to do the model optimization. Some of our optimized models diverges a little from the vllm's modeling, but needs to rewrite several part of original one, brings negligible maintenance bruden to the vllm-ascend.In order to solve that, we propose to leverage `torch.compile` and `inductor pattern matcher`, automatically fuse the pattern we want to merge. For more details can refer to the RFC https://github.com/vllm-project/vllm-ascend/issues/4239 This pr integrates `AddRMSNorm` and the `Quant` operator, which can improve the inference speed of models using `w8a8 `quantization. ### Does this PR introduce _any_ user-facing change? Yes, add new additional_config ### How was this patch tested? ```python def main(): prompts = [ "The president of the United States is Mr.", ] # Create a sampling params object. sampling_params = SamplingParams(max_tokens=100, temperature=0.6, top_k=40, top_p=0.95) # Create an LLM. llm = LLM( model="/root/.cache/modelscope/hub/models/vllm-ascend/Qwen3-8B-W8A8", # enforce_eager=True, tensor_parallel_size=1, trust_remote_code=True, gpu_memory_utilization=0.7, quantization="ascend", ) # 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}") ``` ```text Prompt: 'The president of the United States is Mr.', Generated text: ' Trump. The president of the United States is Mr. Biden. Which of the following statements is correct? \n\nA. Mr. Trump is Mr. Biden. \nB. Mr. Trump is not Mr. Biden. \nC. The president of the United States is not Mr. Trump. \nD. The president of the United States is not Mr. Biden.\n\nThe question presents a contradiction: it states that "The president of the United States is Mr. Trump" and "The president of' ``` - vLLM version: 86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24 - vLLM main: https://github.com/vllm-project/vllm/commit/86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24 --------- Signed-off-by: Icey <1790571317@qq.com> Signed-off-by: wxsIcey <1790571317@qq.com>
2025-12-04 10:29:48 +08:00
ascend_compilation_config = ascend_config.ascend_compilation_config
self.assertTrue(ascend_compilation_config.fuse_norm_quant)
Adopt inductor fusion and define quantization fusion pass (#4168) ### What this PR does / why we need it? The main goal of this PR to alleviate the high maintenance burden from model duplication when we are going to do the model optimization. Some of our optimized models diverges a little from the vllm's modeling, but needs to rewrite several part of original one, brings negligible maintenance bruden to the vllm-ascend.In order to solve that, we propose to leverage `torch.compile` and `inductor pattern matcher`, automatically fuse the pattern we want to merge. For more details can refer to the RFC https://github.com/vllm-project/vllm-ascend/issues/4239 This pr integrates `AddRMSNorm` and the `Quant` operator, which can improve the inference speed of models using `w8a8 `quantization. ### Does this PR introduce _any_ user-facing change? Yes, add new additional_config ### How was this patch tested? ```python def main(): prompts = [ "The president of the United States is Mr.", ] # Create a sampling params object. sampling_params = SamplingParams(max_tokens=100, temperature=0.6, top_k=40, top_p=0.95) # Create an LLM. llm = LLM( model="/root/.cache/modelscope/hub/models/vllm-ascend/Qwen3-8B-W8A8", # enforce_eager=True, tensor_parallel_size=1, trust_remote_code=True, gpu_memory_utilization=0.7, quantization="ascend", ) # 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}") ``` ```text Prompt: 'The president of the United States is Mr.', Generated text: ' Trump. The president of the United States is Mr. Biden. Which of the following statements is correct? \n\nA. Mr. Trump is Mr. Biden. \nB. Mr. Trump is not Mr. Biden. \nC. The president of the United States is not Mr. Trump. \nD. The president of the United States is not Mr. Biden.\n\nThe question presents a contradiction: it states that "The president of the United States is Mr. Trump" and "The president of' ``` - vLLM version: 86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24 - vLLM main: https://github.com/vllm-project/vllm/commit/86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24 --------- Signed-off-by: Icey <1790571317@qq.com> Signed-off-by: wxsIcey <1790571317@qq.com>
2025-12-04 10:29:48 +08:00
@_clean_up_ascend_config
def test_init_ascend_config_with_additional_config(self):
test_vllm_config = VllmConfig()
test_vllm_config.additional_config = {
Adopt inductor fusion and define quantization fusion pass (#4168) ### What this PR does / why we need it? The main goal of this PR to alleviate the high maintenance burden from model duplication when we are going to do the model optimization. Some of our optimized models diverges a little from the vllm's modeling, but needs to rewrite several part of original one, brings negligible maintenance bruden to the vllm-ascend.In order to solve that, we propose to leverage `torch.compile` and `inductor pattern matcher`, automatically fuse the pattern we want to merge. For more details can refer to the RFC https://github.com/vllm-project/vllm-ascend/issues/4239 This pr integrates `AddRMSNorm` and the `Quant` operator, which can improve the inference speed of models using `w8a8 `quantization. ### Does this PR introduce _any_ user-facing change? Yes, add new additional_config ### How was this patch tested? ```python def main(): prompts = [ "The president of the United States is Mr.", ] # Create a sampling params object. sampling_params = SamplingParams(max_tokens=100, temperature=0.6, top_k=40, top_p=0.95) # Create an LLM. llm = LLM( model="/root/.cache/modelscope/hub/models/vllm-ascend/Qwen3-8B-W8A8", # enforce_eager=True, tensor_parallel_size=1, trust_remote_code=True, gpu_memory_utilization=0.7, quantization="ascend", ) # 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}") ``` ```text Prompt: 'The president of the United States is Mr.', Generated text: ' Trump. The president of the United States is Mr. Biden. Which of the following statements is correct? \n\nA. Mr. Trump is Mr. Biden. \nB. Mr. Trump is not Mr. Biden. \nC. The president of the United States is not Mr. Trump. \nD. The president of the United States is not Mr. Biden.\n\nThe question presents a contradiction: it states that "The president of the United States is Mr. Trump" and "The president of' ``` - vLLM version: 86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24 - vLLM main: https://github.com/vllm-project/vllm/commit/86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24 --------- Signed-off-by: Icey <1790571317@qq.com> Signed-off-by: wxsIcey <1790571317@qq.com>
2025-12-04 10:29:48 +08:00
"ascend_compilation_config": {
"fuse_norm_quant": False,
Adopt inductor fusion and define quantization fusion pass (#4168) ### What this PR does / why we need it? The main goal of this PR to alleviate the high maintenance burden from model duplication when we are going to do the model optimization. Some of our optimized models diverges a little from the vllm's modeling, but needs to rewrite several part of original one, brings negligible maintenance bruden to the vllm-ascend.In order to solve that, we propose to leverage `torch.compile` and `inductor pattern matcher`, automatically fuse the pattern we want to merge. For more details can refer to the RFC https://github.com/vllm-project/vllm-ascend/issues/4239 This pr integrates `AddRMSNorm` and the `Quant` operator, which can improve the inference speed of models using `w8a8 `quantization. ### Does this PR introduce _any_ user-facing change? Yes, add new additional_config ### How was this patch tested? ```python def main(): prompts = [ "The president of the United States is Mr.", ] # Create a sampling params object. sampling_params = SamplingParams(max_tokens=100, temperature=0.6, top_k=40, top_p=0.95) # Create an LLM. llm = LLM( model="/root/.cache/modelscope/hub/models/vllm-ascend/Qwen3-8B-W8A8", # enforce_eager=True, tensor_parallel_size=1, trust_remote_code=True, gpu_memory_utilization=0.7, quantization="ascend", ) # 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}") ``` ```text Prompt: 'The president of the United States is Mr.', Generated text: ' Trump. The president of the United States is Mr. Biden. Which of the following statements is correct? \n\nA. Mr. Trump is Mr. Biden. \nB. Mr. Trump is not Mr. Biden. \nC. The president of the United States is not Mr. Trump. \nD. The president of the United States is not Mr. Biden.\n\nThe question presents a contradiction: it states that "The president of the United States is Mr. Trump" and "The president of' ``` - vLLM version: 86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24 - vLLM main: https://github.com/vllm-project/vllm/commit/86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24 --------- Signed-off-by: Icey <1790571317@qq.com> Signed-off-by: wxsIcey <1790571317@qq.com>
2025-12-04 10:29:48 +08:00
},
"multistream_overlap_shared_expert": True,
"expert_map_path": "test_expert_map_path",
"refresh": True,
}
ascend_config = init_ascend_config(test_vllm_config)
self.assertEqual(ascend_config.expert_map_path, "test_expert_map_path")
self.assertTrue(ascend_config.multistream_overlap_shared_expert)
[Feature] Support npuhraph_ex backend (#4700) ### What this PR does / why we need it? We introduced the npugraph_ex backend through the vllm's adaptor dispatch mechanism to accelerate aclgraph. This solution is based on torch.compile and uses torchair to optimize the fx.graph. The performance gains are mainly obtained from the static kernel. We conducted tests on Qwen3-30B and achieved over 5% performance optimization. ### Does this PR introduce _any_ user-facing change? Yes, we add a new switch named"enable_npugraph_ex" in additional_config, default is False. We also add an example to show how to register custom replacement pass ### More information about this PR This feature depends on the release of CANN and torch_npu in Q4. We tested it on a package that has not been publicly released yet and verified that the functionality works. This feature is still experimental at the moment; setting the config true will directly raise error. Merging into the main branch initially involves some preliminary commits to facilitate subsequent development and testing of the feature, as well as to avoid submitting an excessively large PR at once. - vLLM version: v0.12.0 - vLLM main: https://github.com/vllm-project/vllm/commit/ad32e3e19ccf0526cb6744a5fed09a138a5fb2f9 --------- Signed-off-by: chencangtao <chencangtao@huawei.com> Signed-off-by: ChenCangtao <50493711+ChenCangtao@users.noreply.github.com> Co-authored-by: chencangtao <chencangtao@huawei.com> Co-authored-by: panchao-hub <315134829@qq.com> Co-authored-by: wbigat <wbigat@163.com> Co-authored-by: Mengqing Cao <cmq0113@163.com>
2025-12-10 20:48:05 +08:00
self.assertFalse(ascend_config.enable_npugraph_ex)
Adopt inductor fusion and define quantization fusion pass (#4168) ### What this PR does / why we need it? The main goal of this PR to alleviate the high maintenance burden from model duplication when we are going to do the model optimization. Some of our optimized models diverges a little from the vllm's modeling, but needs to rewrite several part of original one, brings negligible maintenance bruden to the vllm-ascend.In order to solve that, we propose to leverage `torch.compile` and `inductor pattern matcher`, automatically fuse the pattern we want to merge. For more details can refer to the RFC https://github.com/vllm-project/vllm-ascend/issues/4239 This pr integrates `AddRMSNorm` and the `Quant` operator, which can improve the inference speed of models using `w8a8 `quantization. ### Does this PR introduce _any_ user-facing change? Yes, add new additional_config ### How was this patch tested? ```python def main(): prompts = [ "The president of the United States is Mr.", ] # Create a sampling params object. sampling_params = SamplingParams(max_tokens=100, temperature=0.6, top_k=40, top_p=0.95) # Create an LLM. llm = LLM( model="/root/.cache/modelscope/hub/models/vllm-ascend/Qwen3-8B-W8A8", # enforce_eager=True, tensor_parallel_size=1, trust_remote_code=True, gpu_memory_utilization=0.7, quantization="ascend", ) # 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}") ``` ```text Prompt: 'The president of the United States is Mr.', Generated text: ' Trump. The president of the United States is Mr. Biden. Which of the following statements is correct? \n\nA. Mr. Trump is Mr. Biden. \nB. Mr. Trump is not Mr. Biden. \nC. The president of the United States is not Mr. Trump. \nD. The president of the United States is not Mr. Biden.\n\nThe question presents a contradiction: it states that "The president of the United States is Mr. Trump" and "The president of' ``` - vLLM version: 86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24 - vLLM main: https://github.com/vllm-project/vllm/commit/86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24 --------- Signed-off-by: Icey <1790571317@qq.com> Signed-off-by: wxsIcey <1790571317@qq.com>
2025-12-04 10:29:48 +08:00
ascend_compilation_config = ascend_config.ascend_compilation_config
self.assertFalse(ascend_compilation_config.fuse_norm_quant)
[Feature] Support npuhraph_ex backend (#4700) ### What this PR does / why we need it? We introduced the npugraph_ex backend through the vllm's adaptor dispatch mechanism to accelerate aclgraph. This solution is based on torch.compile and uses torchair to optimize the fx.graph. The performance gains are mainly obtained from the static kernel. We conducted tests on Qwen3-30B and achieved over 5% performance optimization. ### Does this PR introduce _any_ user-facing change? Yes, we add a new switch named"enable_npugraph_ex" in additional_config, default is False. We also add an example to show how to register custom replacement pass ### More information about this PR This feature depends on the release of CANN and torch_npu in Q4. We tested it on a package that has not been publicly released yet and verified that the functionality works. This feature is still experimental at the moment; setting the config true will directly raise error. Merging into the main branch initially involves some preliminary commits to facilitate subsequent development and testing of the feature, as well as to avoid submitting an excessively large PR at once. - vLLM version: v0.12.0 - vLLM main: https://github.com/vllm-project/vllm/commit/ad32e3e19ccf0526cb6744a5fed09a138a5fb2f9 --------- Signed-off-by: chencangtao <chencangtao@huawei.com> Signed-off-by: ChenCangtao <50493711+ChenCangtao@users.noreply.github.com> Co-authored-by: chencangtao <chencangtao@huawei.com> Co-authored-by: panchao-hub <315134829@qq.com> Co-authored-by: wbigat <wbigat@163.com> Co-authored-by: Mengqing Cao <cmq0113@163.com>
2025-12-10 20:48:05 +08:00
@_clean_up_ascend_config
def test_init_ascend_config_enable_npugraph_ex(self):
with self.assertRaises(NotImplementedError):
test_vllm_config = VllmConfig()
test_vllm_config.additional_config = {
"enable_npugraph_ex": True,
"refresh": True,
}
init_ascend_config(test_vllm_config)
@_clean_up_ascend_config
def test_get_ascend_config(self):
test_vllm_config = VllmConfig()
ascend_config = init_ascend_config(test_vllm_config)
self.assertEqual(get_ascend_config(), ascend_config)
@_clean_up_ascend_config
def test_get_ascend_config_without_init(self):
with self.assertRaises(RuntimeError):
get_ascend_config()
@_clean_up_ascend_config
def test_clear_ascend_config(self):
test_vllm_config = VllmConfig()
ascend_config = init_ascend_config(test_vllm_config)
self.assertEqual(get_ascend_config(), ascend_config)
clear_ascend_config()
with self.assertRaises(RuntimeError):
get_ascend_config()