From 5442b463fd7b232fc560dd549e50b737043992cb Mon Sep 17 00:00:00 2001 From: Shuqiao Li Date: Mon, 21 Apr 2025 10:33:38 +0800 Subject: [PATCH] add doc for patch_config (#574) ### 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 --- vllm_ascend/patch/platform/patch_0_8_4/__init__.py | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/vllm_ascend/patch/platform/patch_0_8_4/__init__.py b/vllm_ascend/patch/platform/patch_0_8_4/__init__.py index cdbe66f..9e6adeb 100644 --- a/vllm_ascend/patch/platform/patch_0_8_4/__init__.py +++ b/vllm_ascend/patch/platform/patch_0_8_4/__init__.py @@ -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 \ No newline at end of file +import vllm_ascend.patch.platform.patch_0_8_4.patch_distributed # noqa