huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 20:34:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix dockerfiles

Browse Source
This commit is contained in:
OlivierDehaene 2024-06-05 10:20:44 +02:00
parent 9410a79df4
commit eb6a02a0f1
4 changed files with 16 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
Dockerfile
View File

@ -25,7 +25,7 @@ RUN PROTOC_ZIP=protoc-21.12-linux-x86_64.zip && \
rm -f $PROTOC_ZIP rm -f $PROTOC_ZIP
COPY --from=planner /usr/src/recipe.json recipe.json COPY --from=planner /usr/src/recipe.json recipe.json
RUN cargo chef cook --release --recipe-path recipe.json RUN cargo chef cook --profile release-opt --recipe-path recipe.json
COPY Cargo.toml Cargo.toml COPY Cargo.toml Cargo.toml
COPY rust-toolchain.toml rust-toolchain.toml COPY rust-toolchain.toml rust-toolchain.toml
@ -226,11 +226,11 @@ RUN cd server && \
pip install ".[bnb, accelerate, quantize, peft, outlines]" --no-cache-dir pip install ".[bnb, accelerate, quantize, peft, outlines]" --no-cache-dir
# Install benchmarker # Install benchmarker
COPY --from=builder /usr/src/target/release/text-generation-benchmark /usr/local/bin/text-generation-benchmark COPY --from=builder /usr/src/target/release-opt/text-generation-benchmark /usr/local/bin/text-generation-benchmark
# Install router # Install router
COPY --from=builder /usr/src/target/release/text-generation-router /usr/local/bin/text-generation-router COPY --from=builder /usr/src/target/release-opt/text-generation-router /usr/local/bin/text-generation-router
# Install launcher # Install launcher
COPY --from=builder /usr/src/target/release/text-generation-launcher /usr/local/bin/text-generation-launcher COPY --from=builder /usr/src/target/release-opt/text-generation-launcher /usr/local/bin/text-generation-launcher
RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \ RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
build-essential \ build-essential \

8
Dockerfile_amd
View File

@ -25,7 +25,7 @@ RUN PROTOC_ZIP=protoc-21.12-linux-x86_64.zip && \
rm -f $PROTOC_ZIP rm -f $PROTOC_ZIP
COPY --from=planner /usr/src/recipe.json recipe.json COPY --from=planner /usr/src/recipe.json recipe.json
RUN cargo chef cook --release --recipe-path recipe.json RUN cargo chef cook --profile release-opt --recipe-path recipe.json
COPY Cargo.toml Cargo.toml COPY Cargo.toml Cargo.toml
COPY rust-toolchain.toml rust-toolchain.toml COPY rust-toolchain.toml rust-toolchain.toml
@ -193,11 +193,11 @@ RUN cd server && \
pip install ".[accelerate, peft, outlines]" --no-cache-dir pip install ".[accelerate, peft, outlines]" --no-cache-dir
# Install benchmarker # Install benchmarker
COPY --from=builder /usr/src/target/release/text-generation-benchmark /usr/local/bin/text-generation-benchmark COPY --from=builder /usr/src/target/release-opt/text-generation-benchmark /usr/local/bin/text-generation-benchmark
# Install router # Install router
COPY --from=builder /usr/src/target/release/text-generation-router /usr/local/bin/text-generation-router COPY --from=builder /usr/src/target/release-opt/text-generation-router /usr/local/bin/text-generation-router
# Install launcher # Install launcher
COPY --from=builder /usr/src/target/release/text-generation-launcher /usr/local/bin/text-generation-launcher COPY --from=builder /usr/src/target/release-opt/text-generation-launcher /usr/local/bin/text-generation-launcher
# AWS Sagemaker compatible image # AWS Sagemaker compatible image
FROM base as sagemaker FROM base as sagemaker

8
Dockerfile_intel
View File

@ -24,7 +24,7 @@ RUN PROTOC_ZIP=protoc-21.12-linux-x86_64.zip && \
rm -f $PROTOC_ZIP rm -f $PROTOC_ZIP
COPY --from=planner /usr/src/recipe.json recipe.json COPY --from=planner /usr/src/recipe.json recipe.json
RUN cargo chef cook --release --recipe-path recipe.json RUN cargo chef cook --profile release-opt --recipe-path recipe.json
COPY Cargo.toml Cargo.toml COPY Cargo.toml Cargo.toml
COPY rust-toolchain.toml rust-toolchain.toml COPY rust-toolchain.toml rust-toolchain.toml
@ -78,11 +78,11 @@ ENV PATH=/opt/intel/oneapi/mpi/latest/opt/mpi/libfabric/bin:/opt/intel/oneapi/mp
ENV CCL_ZE_IPC_EXCHANGE=sockets ENV CCL_ZE_IPC_EXCHANGE=sockets
# Install benchmarker # Install benchmarker
COPY --from=builder /usr/src/target/release/text-generation-benchmark /usr/local/bin/text-generation-benchmark COPY --from=builder /usr/src/target/release-opt/text-generation-benchmark /usr/local/bin/text-generation-benchmark
# Install router # Install router
COPY --from=builder /usr/src/target/release/text-generation-router /usr/local/bin/text-generation-router COPY --from=builder /usr/src/target/release-opt/text-generation-router /usr/local/bin/text-generation-router
# Install launcher # Install launcher
COPY --from=builder /usr/src/target/release/text-generation-launcher /usr/local/bin/text-generation-launcher COPY --from=builder /usr/src/target/release-opt/text-generation-launcher /usr/local/bin/text-generation-launcher
# Final image # Final image
FROM base FROM base

14
router/src/infer/v3/queue.rs
View File

@ -14,7 +14,7 @@ use text_generation_client::ChunksToString;
use text_generation_client::Input; use text_generation_client::Input;
use tokio::sync::{mpsc, oneshot}; use tokio::sync::{mpsc, oneshot};
use tokio::time::Instant; use tokio::time::Instant;
use tracing::{info_span, instrument, Span}; use tracing::{info_span, instrument, Instrument, Span};
/// Queue entry /// Queue entry
#[derive(Debug)] #[derive(Debug)]
@ -136,9 +136,9 @@ async fn queue_task(
response_sender, response_sender,
span, span,
} => { } => {
let _parent_span = span.enter();
let next_batch = state let next_batch = state
.next_batch(min_size, max_size, prefill_token_budget, token_budget) .next_batch(min_size, max_size, prefill_token_budget, token_budget)
.instrument(span)
.await; .await;
response_sender.send(next_batch).unwrap(); response_sender.send(next_batch).unwrap();
metrics::gauge!("tgi_queue_size", state.entries.len() as f64); metrics::gauge!("tgi_queue_size", state.entries.len() as f64);
@ -180,14 +180,8 @@ impl State {
speculate: u32, speculate: u32,
max_batch_total_tokens: u32, max_batch_total_tokens: u32,
) -> Self { ) -> Self {
let block_allocator = match requires_padding { let block_allocator = requires_padding
true => None, .then(|| BlockAllocator::new(max_batch_total_tokens, block_size, window_size));
false => Some(BlockAllocator::new(
max_batch_total_tokens,
block_size,
window_size,
)),
};
Self { Self {
entries: VecDeque::with_capacity(128), entries: VecDeque::with_capacity(128),