Skip to content

Update Dockerfile-cuda-all to support 89 #674

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

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Update Dockerfile-cuda-all to support 89 #674

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
bcd61a5
Update Dockerfile-cuda-all
pocman Jul 3, 2025
d25aa76
Update cuda-all-entrypoint.sh
pocman Jul 3, 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
21 changes: 21 additions & 0 deletions Dockerfile-cuda-all
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -76,6 +76,15 @@ RUN --mount=type=secret,id=actions_results_url,env=ACTIONS_RESULTS_URL \
CUDA_COMPUTE_CAP=80 cargo chef cook --release --features candle-cuda --recipe-path recipe.json && sccache -s; \
fi;

RUN --mount=type=secret,id=actions_results_url,env=ACTIONS_RESULTS_URL \
--mount=type=secret,id=actions_runtime_token,env=ACTIONS_RUNTIME_TOKEN \
if [ $VERTEX = "true" ]; \
then \
CUDA_COMPUTE_CAP=89 cargo chef cook --release --features google --features candle-cuda --recipe-path recipe.json && sccache -s; \
else \
CUDA_COMPUTE_CAP=89 cargo chef cook --release --features candle-cuda --recipe-path recipe.json && sccache -s; \
fi;

RUN --mount=type=secret,id=actions_results_url,env=ACTIONS_RESULTS_URL \
--mount=type=secret,id=actions_runtime_token,env=ACTIONS_RUNTIME_TOKEN \
if [ $VERTEX = "true" ]; \
Expand Down Expand Up @@ -113,6 +122,17 @@ RUN --mount=type=secret,id=actions_results_url,env=ACTIONS_RESULTS_URL \

RUN mv /usr/src/target/release/text-embeddings-router /usr/src/target/release/text-embeddings-router-80

RUN --mount=type=secret,id=actions_results_url,env=ACTIONS_RESULTS_URL \
--mount=type=secret,id=actions_runtime_token,env=ACTIONS_RUNTIME_TOKEN \
if [ $VERTEX = "true" ]; \
then \
CUDA_COMPUTE_CAP=89 cargo build --release --bin text-embeddings-router -F candle-cuda -F google && sccache -s; \
else \
CUDA_COMPUTE_CAP=89 cargo build --release --bin text-embeddings-router -F candle-cuda && sccache -s; \
fi;

RUN mv /usr/src/target/release/text-embeddings-router /usr/src/target/release/text-embeddings-router-89

RUN --mount=type=secret,id=actions_results_url,env=ACTIONS_RESULTS_URL \
--mount=type=secret,id=actions_runtime_token,env=ACTIONS_RUNTIME_TOKEN \
if [ $VERTEX = "true" ]; \
Expand Down Expand Up @@ -140,6 +160,7 @@ RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-ins

COPY --from=builder /usr/src/target/release/text-embeddings-router-75 /usr/local/bin/text-embeddings-router-75
COPY --from=builder /usr/src/target/release/text-embeddings-router-80 /usr/local/bin/text-embeddings-router-80
COPY --from=builder /usr/src/target/release/text-embeddings-router-89 /usr/local/bin/text-embeddings-router-89
COPY --from=builder /usr/src/target/release/text-embeddings-router-90 /usr/local/bin/text-embeddings-router-90

# Amazon SageMaker compatible image
Expand Down
5 changes: 4 additions & 1 deletion cuda-all-entrypoint.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,9 +10,12 @@ compute_cap=$(nvidia-smi --query-gpu=compute_cap --format=csv | sed -n '2p' | se
if [ ${compute_cap} -eq 75 ]
then
exec text-embeddings-router-75 "$@"
elif [ ${compute_cap} -ge 80 -a ${compute_cap} -lt 90 ]
elif [ ${compute_cap} -ge 80 -a ${compute_cap} -lt 89 ]
then
exec text-embeddings-router-80 "$@"
elif [ ${compute_cap} -ge 89 -a ${compute_cap} -lt 90 ]
then
exec text-embeddings-router-89 "$@"
elif [ ${compute_cap} -eq 90 ]
then
exec text-embeddings-router-90 "$@"
Expand Down