Skip to content

feat: Shrink the ai-dynamo wheel by 35 MiB #1918

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
merged 1 commit into from
Jul 14, 2025
Merged

feat: Shrink the ai-dynamo wheel by 35 MiB #1918

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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: 0 additions & 2 deletions .devcontainer/post-create.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,8 +55,6 @@ cargo doc --no-deps
# create symlinks for the binaries in the deploy directory
mkdir -p $HOME/dynamo/deploy/sdk/src/dynamo/sdk/cli/bin
ln -sf $HOME/dynamo/.build/target/debug/dynamo-run $HOME/dynamo/deploy/sdk/src/dynamo/sdk/cli/bin/dynamo-run
ln -sf $HOME/dynamo/.build/target/debug/http $HOME/dynamo/deploy/sdk/src/dynamo/sdk/cli/bin/http
ln -sf $HOME/dynamo/.build/target/debug/llmctl $HOME/dynamo/deploy/sdk/src/dynamo/sdk/cli/bin/llmctl

# install the python bindings
cd $HOME/dynamo/lib/bindings/python && retry maturin develop
Expand Down
67 changes: 0 additions & 67 deletions Cargo.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

1 change: 0 additions & 1 deletion Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,6 @@

[workspace]
members = [
"components/http",
"components/metrics",
"components/router",
"launch/*",
Expand Down
4 changes: 1 addition & 3 deletions Earthfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -120,9 +120,7 @@ dynamo-build:
# Remove existing symlinks
rm -f /workspace/deploy/sdk/src/dynamo/sdk/cli/bin/* && \
# Create new symlinks pointing to the correct location
ln -sf /workspace/target/release/dynamo-run /workspace/deploy/sdk/src/dynamo/sdk/cli/bin/dynamo-run && \
ln -sf /workspace/target/release/http /workspace/deploy/sdk/src/dynamo/sdk/cli/bin/http && \
ln -sf /workspace/target/release/llmctl /workspace/deploy/sdk/src/dynamo/sdk/cli/bin/llmctl
ln -sf /workspace/target/release/dynamo-run /workspace/deploy/sdk/src/dynamo/sdk/cli/bin/dynamo-run


RUN cd /workspace/lib/bindings/python && \
Expand Down
2 changes: 0 additions & 2 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -172,8 +172,6 @@ Otherwise, to develop locally, we recommend working inside of the container

cargo build --release
mkdir -p /workspace/deploy/sdk/src/dynamo/sdk/cli/bin
cp /workspace/target/release/http /workspace/deploy/sdk/src/dynamo/sdk/cli/bin
cp /workspace/target/release/llmctl /workspace/deploy/sdk/src/dynamo/sdk/cli/bin
cp /workspace/target/release/dynamo-run /workspace/deploy/sdk/src/dynamo/sdk/cli/bin

uv pip install -e .
Expand Down
34 changes: 0 additions & 34 deletions components/http/Cargo.toml
View file
Open in desktop

This file was deleted.

73 changes: 0 additions & 73 deletions components/http/src/main.rs
View file
Open in desktop

This file was deleted.

2 changes: 0 additions & 2 deletions container/Dockerfile.none
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,8 +49,6 @@ ENV CARGO_TARGET_DIR=/workspace/target
RUN cargo build --release --locked && \
cargo doc --no-deps && \
cp target/release/dynamo-run /usr/local/bin && \
cp target/release/http /usr/local/bin && \
cp target/release/llmctl /usr/local/bin && \
cp target/release/metrics /usr/local/bin && \
cp target/release/mock_worker /usr/local/bin

Expand Down
2 changes: 0 additions & 2 deletions container/Dockerfile.sglang
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -367,8 +367,6 @@ RUN mkdir -p /opt/dynamo/bindings/wheels && \
cp target/release/libdynamo_llm_capi.so /opt/dynamo/bindings/lib/. && \
cp -r lib/bindings/c/include /opt/dynamo/bindings/. && \
cp target/release/dynamo-run /usr/local/bin && \
cp target/release/http /usr/local/bin && \
cp target/release/llmctl /usr/local/bin && \
cp target/release/metrics /usr/local/bin && \
cp target/release/mock_worker /usr/local/bin

Expand Down
2 changes: 0 additions & 2 deletions container/Dockerfile.sglang-deepep
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -132,8 +132,6 @@ ENV CARGO_BUILD_JOBS=${CARGO_BUILD_JOBS:-16}

RUN cargo build --release
RUN mkdir -p deploy/sdk/src/dynamo/sdk/cli/bin
RUN cp target/release/http deploy/sdk/src/dynamo/sdk/cli/bin
RUN cp target/release/llmctl deploy/sdk/src/dynamo/sdk/cli/bin
RUN cp target/release/dynamo-run deploy/sdk/src/dynamo/sdk/cli/bin

RUN cd lib/bindings/python && pip install --break-system-packages -e . && cd ../../..
Expand Down
2 changes: 0 additions & 2 deletions container/Dockerfile.tensorrt_llm
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -317,8 +317,6 @@ RUN mkdir -p /opt/dynamo/bindings/wheels && \
cp target/release/libdynamo_llm_capi.so /opt/dynamo/bindings/lib/. && \
cp -r lib/bindings/c/include /opt/dynamo/bindings/. && \
cp target/release/dynamo-run /usr/local/bin && \
cp target/release/http /usr/local/bin && \
cp target/release/llmctl /usr/local/bin && \
cp target/release/metrics /usr/local/bin && \
cp target/release/mock_worker /usr/local/bin

Expand Down
2 changes: 0 additions & 2 deletions container/Dockerfile.vllm
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -432,8 +432,6 @@ RUN mkdir -p /opt/dynamo/bindings/wheels && \
cp target/release/libdynamo_llm_capi.so /opt/dynamo/bindings/lib/. && \
cp -r lib/bindings/c/include /opt/dynamo/bindings/. && \
cp target/release/dynamo-run /usr/local/bin && \
cp target/release/http /usr/local/bin && \
cp target/release/llmctl /usr/local/bin && \
cp target/release/metrics /usr/local/bin && \
cp target/release/mock_worker /usr/local/bin

Expand Down
2 changes: 0 additions & 2 deletions container/Dockerfile.vllm_v1
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -412,8 +412,6 @@ RUN mkdir -p /opt/dynamo/bindings/wheels && \
cp target/release/libdynamo_llm_capi.so /opt/dynamo/bindings/lib/. && \
cp -r lib/bindings/c/include /opt/dynamo/bindings/. && \
cp target/release/dynamo-run /usr/local/bin && \
cp target/release/http /usr/local/bin && \
cp target/release/llmctl /usr/local/bin && \
cp target/release/metrics /usr/local/bin && \
cp target/release/mock_worker /usr/local/bin

Expand Down
22 changes: 0 additions & 22 deletions deploy/sdk/src/dynamo/sdk/cli/run_executable.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,28 +69,6 @@ def dynamo_run(args=None):
return result.returncode


def llmctl(args=None):
"""
Run the llmctl executable with the provided arguments.
If no args provided, passes through sys.argv[1:] to the executable.
"""
if args is None:
args = sys.argv[1:]
result = run_executable("llmctl", args=args, capture_output=False)
return result.returncode


def http(args=None):
"""
Run the http executable with the provided arguments.
If no args provided, passes through sys.argv[1:] to the executable.
"""
if args is None:
args = sys.argv[1:]
result = run_executable("http", args=args, capture_output=False)
return result.returncode


def metrics(args=None):
"""
Run the metrics executable with the provided arguments.
Expand Down
2 changes: 0 additions & 2 deletions docs/get_started.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -206,8 +206,6 @@ Otherwise, to develop locally, we recommend working inside of the container:

cargo build --release
mkdir -p /workspace/deploy/dynamo/sdk/src/dynamo/sdk/cli/bin
cp /workspace/target/release/http /workspace/deploy/dynamo/sdk/src/dynamo/sdk/cli/bin
cp /workspace/target/release/llmctl /workspace/deploy/dynamo/sdk/src/dynamo/sdk/cli/bin
cp /workspace/target/release/dynamo-run /workspace/deploy/dynamo/sdk/src/dynamo/sdk/cli/bin

uv pip install -e .
Expand Down
4 changes: 0 additions & 4 deletions docs/guides/backend.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -92,10 +92,6 @@ class ResponseType(BaseModel):
# Add other fields as needed
```

For example, if you deploy your worker directly behind an OpenAI HTTP (`http`) service
using `llmctl`, you can define the request and response types to correspond to
Chat Completions objects, such as the ones specified in the OpenAI API. For example:

```python
from vllm.entrypoints.openai.protocol import ChatCompletionRequest

Expand Down
2 changes: 0 additions & 2 deletions hatch_build.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,8 +24,6 @@ def initialize(self, version, build_data):
bin_path = os.getenv("DYNAMO_BIN_PATH", "target/release")
build_data["force_include"] = {
f"{bin_path}/dynamo-run": "dynamo/sdk/cli/bin/dynamo-run",
f"{bin_path}/llmctl": "dynamo/sdk/cli/bin/llmctl",
f"{bin_path}/http": "dynamo/sdk/cli/bin/http",
f"{bin_path}/metrics": "dynamo/sdk/cli/bin/metrics",
f"{bin_path}/mock_worker": "dynamo/sdk/cli/bin/mock_worker",
f"{bin_path}/libdynamo_llm_capi.so": "dynamo/sdk/cli/bin/libdynamo_llm_capi.so",
Expand Down
36 changes: 0 additions & 36 deletions launch/llmctl/Cargo.toml
View file
Open in desktop

This file was deleted.

Loading
Loading