Skip to content

Enhance Dockerfile to manage tokenizers binary download #488

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

Draft
wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

Enhance Dockerfile to manage tokenizers binary download #488

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
17 changes: 16 additions & 1 deletion Dockerfile.epp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,22 @@ RUN scripts/fetch-python-wrapper.sh ${KVCACHE_MANAGER_VERSION} /workspace/llm-d-
RUN mkdir -p lib
# Ensure that the RELEASE_VERSION matches the one used in the imported llm-d-kv-cache-manager version
ARG RELEASE_VERSION=v1.22.1
RUN curl -L https://github.com/daulet/tokenizers/releases/download/${RELEASE_VERSION}/libtokenizers.${TARGETOS}-${TARGETARCH}.tar.gz | tar -xz -C lib
# Handle ppc64le or missing prebuilt binaries
Copy link
Contributor

@zdtsw zdtsw Nov 25, 2025

Choose a reason for hiding this comment

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

isnt the avaiable release for v1.22.1 only for arm64 and amd64 ?
so you should uplift RELEASE_VERSION to v1.24.0 instead adding build-from-source

Copy link
Contributor

@zdtsw zdtsw Nov 25, 2025

Choose a reason for hiding this comment

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

@vMaroon do we have plan uplift to 1.24.0 https://github.com/llm-d/llm-d-kv-cache-manager/blob/main/go.mod#L8

RUN set -eux; \
URL="https://github.com/daulet/tokenizers/releases/download/${RELEASE_VERSION}/libtokenizers.${TARGETOS}-${TARGETARCH}.tar.gz"; \
echo "Attempting to download prebuilt tokenizers binary from $URL"; \
if curl -fL "$URL" -o /tmp/libtokenizers.tar.gz; then \
echo "Extracting prebuilt libtokenizers..."; \
tar -xz -C lib -f /tmp/libtokenizers.tar.gz; \
else \
echo "No prebuilt libtokenizers found for ${TARGETARCH}, building from source..."; \
dnf install -y rust cargo make cmake && \
git clone --depth 1 --branch ${RELEASE_VERSION} https://github.com/daulet/tokenizers.git /tmp/tokenizers && \
cd /tmp/tokenizers && \
cargo build --release && \
cp target/release/libtokenizers.* /workspace/lib/ && \
cd /workspace && rm -rf /tmp/tokenizers; \
fi
RUN ranlib lib/*.a

# Build
Expand Down