huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-09 11:24:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

faster builds

Browse Source
This commit is contained in:
OlivierDehaene 2023-03-03 14:31:27 +01:00
parent 787e20a199
commit 18e8f03070
2 changed files with 24 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
.github/workflows/build.yaml vendored
View File

@ -15,6 +15,10 @@ jobs:
build-and-push-image:
runs-on: ubuntu-latest
steps:
- name: Initialize Docker Buildx
uses: docker/setup-buildx-action@v2.0.0
with:
install: true
- name: Tailscale
uses: tailscale/github-action@v1
with:
@ -65,5 +69,5 @@ jobs:
platforms: 'linux/amd64'
tags: ${{ steps.meta.outputs.tags }}
labels: ${{ steps.meta.outputs.labels }}
cache-from: type=registry,ref=ghcr.io/huggingface/text-generation-inference:latest
cache-to: type=inline
cache-from: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache,mode=max
cache-to: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache,mode=max

36
Dockerfile
View File

@ -1,4 +1,15 @@
FROM rust:1.67 as router-builder
FROM lukemathwalker/cargo-chef:latest-rust-1.67 AS chef
WORKDIR /usr/src
FROM chef as planner
COPY Cargo.toml Cargo.toml
COPY rust-toolchain.toml rust-toolchain.toml
COPY proto proto
COPY router router
COPY launcher launcher
RUN cargo chef prepare --recipe-path recipe.json
FROM chef AS builder
RUN PROTOC_ZIP=protoc-21.12-linux-x86_64.zip && \
curl -OL https://github.com/protocolbuffers/protobuf/releases/download/v21.12/$PROTOC_ZIP && \
@ -6,26 +17,15 @@ RUN PROTOC_ZIP=protoc-21.12-linux-x86_64.zip && \
unzip -o $PROTOC_ZIP -d /usr/local 'include/*' && \
rm -f $PROTOC_ZIP
WORKDIR /usr/src
COPY --from=planner /usr/src/recipe.json recipe.json
RUN cargo chef cook --release --recipe-path recipe.json
COPY Cargo.toml Cargo.toml
COPY rust-toolchain.toml rust-toolchain.toml
COPY proto proto
COPY router router
WORKDIR /usr/src/router
RUN cargo install --path .
FROM rust:1.67 as launcher-builder
WORKDIR /usr/src
COPY rust-toolchain.toml rust-toolchain.toml
COPY launcher launcher
WORKDIR /usr/src/launcher
RUN cargo install --path .
RUN cargo build --release
FROM nvidia/cuda:11.8.0-devel-ubuntu22.04
@ -69,9 +69,9 @@ RUN cd server && \
/opt/miniconda/envs/text-generation/bin/pip install ".[bnb]" --no-cache-dir
# Install router
COPY --from=router-builder /usr/local/cargo/bin/text-generation-router /usr/local/bin/text-generation-router
COPY --from=builder /usr/src/target/release/text-generation-router /usr/local/bin/text-generation-router
# Install launcher
COPY --from=launcher-builder /usr/local/cargo/bin/text-generation-launcher /usr/local/bin/text-generation-launcher
COPY --from=builder /usr/src/target/release/text-generation-launcher /usr/local/bin/text-generation-launcher
ENTRYPOINT ["text-generation-launcher"]
CMD ["--json-output"]