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

add doc for patch_config (#574)

Browse Source 
### What this PR does / why we need it?
add doc for patch_config
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
No code changed.

Signed-off-by: Shuqiao Li <celestialli@outlook.com>
This commit is contained in:
Shuqiao Li
2025-04-21 10:33:38 +08:00
committed by GitHub
parent 96d6fa7c90
commit 5442b463fd
1 changed files with 12 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
vllm_ascend/patch/platform/patch_0_8_4/__init__.py
View File

@@ -14,6 +14,17 @@
# See the License for the specific language governing permissions and
# limitations under the License.
#
# What's Patched and how it works:
# ** File: platform/patch_0_8_4/patch_config.py**
# 1. `vllm.config.ModelConfig.__init__()`
# Why:
# It is hard coded for sleep mode to support cuda platform only
# How：
# Using a new method to check if sleep mode is available
# Related PR (if no, explain why): 1. refused by vllm. 2. vllm doesn't support 3. prepare to submit....
# https://github.com/vllm-project/vllm/pull/16562
# Future Plan:
# This patch is only used for 084 and can't be revert. just keep as it is.
import vllm_ascend.patch.platform.patch_0_8_4.patch_config # noqa
import vllm_ascend.patch.platform.patch_0_8_4.patch_distributed # noqa
import vllm_ascend.patch.platform.patch_0_8_4.patch_distributed # noqa