Skip to content

fix: coordinate autotune_warmup sequence #1156

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
hiworldwzj merged 3 commits into from
Dec 24, 2025
Merged

fix: coordinate autotune_warmup sequence #1156

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
fb87d36
fix: coordinate autotune_warmup sequence
Dec 23, 2025
2bd6cb1
fix
hiworldwzj Dec 24, 2025
58f8df8
fix
Dec 24, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion docker/cuda_version_12.8.0/Dockerfile.nixl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,7 +81,7 @@ RUN apt-get update && apt-get install -y cmake automake autotools-dev libtool l
RUN apt-get update && apt-get install -y pkg-config tmux net-tools libaio-dev ; \
cd /usr/local/src; \
pip install --upgrade meson pybind11 patchelf; \
git clone https://github.com/ai-dynamo/nixl.git -b main && \
git clone https://github.com/ai-dynamo/nixl.git -b 0.8.0 && \
cd nixl && \
rm -rf build && \
mkdir build && \
Expand Down
2 changes: 1 addition & 1 deletion docker/cuda_version_12.8.0/Dockerfile.nixl.deepep
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -108,7 +108,7 @@ RUN apt-get update && apt-get install -y cmake automake autotools-dev libtool l
RUN apt-get update && apt-get install -y pkg-config tmux net-tools libaio-dev ; \
cd /usr/local/src; \
pip install --upgrade meson pybind11 patchelf; \
git clone https://github.com/ai-dynamo/nixl.git -b main && \
git clone https://github.com/ai-dynamo/nixl.git -b 0.8.0 && \
cd nixl && \
rm -rf build && \
mkdir build && \
Expand Down
2 changes: 1 addition & 1 deletion docker/cuda_version_12.8.0/Dockerfile.nixl.deepep.cache
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -110,7 +110,7 @@ RUN apt-get update && apt-get install -y cmake automake autotools-dev libtool l
RUN apt-get update && apt-get install -y pkg-config tmux net-tools libaio-dev ; \
cd /usr/local/src; \
pip install --upgrade meson pybind11 patchelf; \
git clone https://github.com/ai-dynamo/nixl.git -b main && \
git clone https://github.com/ai-dynamo/nixl.git -b 0.8.0 && \
cd nixl && \
rm -rf build && \
mkdir build && \
Expand Down
4 changes: 2 additions & 2 deletions lightllm/common/basemodel/basemodel.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -112,10 +112,10 @@ def __init__(self, kvargs):
self._init_some_value()
self._init_custom()
self._init_inferstate_cls()
self._autotune_warmup()
self._init_padded_req()
# wait必须在init cudagraph 之前，避免错误捕获
self._wait_other_modules_ready()
self._autotune_warmup()
self._init_padded_req()
self._init_cudagraph()
self._init_prefill_cuda_graph()
self._check_max_len_infer()
Expand Down
3 changes: 2 additions & 1 deletion requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -92,4 +92,5 @@ torchvision==0.23.0
interegular==0.3.3
partial_json_parser==0.2.1.1.post6
websockets==15.0.1
cupy-cuda12x==13.6.0
cupy-cuda12x==13.6.0
nixl==0.8.0
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot Dec 23, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

critical

The nixl dependency is added here, but it appears nixl is not available on PyPI or the specified extra index. The Dockerfiles build nixl from source later in the build process. The pip install -r requirements.txt command, which runs before the source build, will fail because it cannot find a matching distribution for nixl==0.8.0. This will break the Docker image build. Since nixl is installed from source in the Dockerfiles, this line should be removed to prevent build failures.