EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[Quantization] Support compressed tensors w8a8 static and w8a8 dynamic weight (#4036)

Browse Source 
### What this PR does / why we need it?

While using the LLM Compressor quantization tool from the VLLM community
to generate quantized weights, the VLLM Ascend engine needs to be
adapted to support the compressed tensors quantization format.

1. Add AscendCompressedTensorsConfig to replace CompressedTensorsConfig
in vllm.
2. Support CompressedTensorsW8A8 static weight.
- weight: per-channel, int8, symmetric; activation: per-tensor, int8,
symmetric.
4. Support CompressedTensorsW8A8Dynamic weight.
- weight: per-channel, int8, symmetric; activation: per-token, int8,
symmetric, dynamic.
5. Modify the override_quantization_method in AscendQuantConfig.

Co-authored-by: taoqun110 taoqun@huawei.com
Co-authored-by: chenxi-hh chen464822955@163.com

- vLLM version: v0.11.2

---------

Signed-off-by: LHXuuu <scut_xlh@163.com>
Signed-off-by: chenxi-hh <chen464822955@163.com>
Signed-off-by: chenxi-hh <32731611+chenxi-hh@users.noreply.github.com>
Co-authored-by: chenxi-hh <chen464822955@163.com>
Co-authored-by: chenxi-hh <32731611+chenxi-hh@users.noreply.github.com>
This commit is contained in:
LHXuuu
2025-11-28 14:09:39 +08:00
committed by GitHub
parent ab37a7d5ae
commit bdc66972db
18 changed files with 707 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
tests/ut/test_platform.py
View File

@@ -9,7 +9,8 @@ from vllm.platforms import PlatformEnum
from tests.ut.base import TestBase
from vllm_ascend.platform import NPUPlatform
from vllm_ascend.utils import ASCEND_QUANTIZATION_METHOD, AscendDeviceType
from vllm_ascend.utils import (ASCEND_QUANTIZATION_METHOD,
COMPRESSED_TENSORS_METHOD, AscendDeviceType)
class TestNPUPlatform(TestBase):
@@ -47,8 +48,9 @@ class TestNPUPlatform(TestBase):
self.assertEqual(NPUPlatform.device_control_env_var,
"ASCEND_RT_VISIBLE_DEVICES")
self.assertEqual(NPUPlatform.dispatch_key, "PrivateUse1")
self.assertEqual(NPUPlatform.supported_quantization,
[ASCEND_QUANTIZATION_METHOD])
self.assertEqual(
NPUPlatform.supported_quantization,
[ASCEND_QUANTIZATION_METHOD, COMPRESSED_TENSORS_METHOD])
def test_is_sleep_mode_available(self):
self.assertTrue(self.platform.is_sleep_mode_available())