text-generation-inference/Dockerfile_llamacpp
Adrien Gallouët cfd4fbb479
[Backend] Add Llamacpp backend (#2975)
* Add llamacpp backend

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Get rid of llama_batch_get_one()

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Use max_batch_total_tokens

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Handle max_batch_size

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Add some input validation checks

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Handle ctx args & fix sampling

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Add GPU args

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Add --defrag-threshold

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Add a stupid batch mechanism

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Cleanup

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Add --numa

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Fix args

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Enable flash attention by default

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Add --offload-kqv

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Fix batch_pos

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* backend(llama): add CUDA Dockerfile_llamacpp for now

* Only export the latest logits

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Output real logprobs

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Fix batching

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Fix seq iterations

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Auto-detect n_threads when not provided

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Clear request cache after completion

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Remove warmup

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Cleanup

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* backend(llama): add CUDA architectures build argument for Dockerfile

* Add specific args for batch

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Add --type-v & --type-k

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Bump llamacpp to b4623

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Disable graceful shutdown in debug mode

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Update Dockerfile_llamacpp

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Cleanup Dockerfile

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Update Cargo.lock

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Update args

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Simplify batching logic

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Set TGI_LLAMA_PKG_CUDA from CUDA_VERSION

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Rename bindings

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Remove n_ctx

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Make max_batch_total_tokens optional

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Ensure all samplers are freed on error

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Initialize penalty_last_n with llamacpp default value

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Cleanup

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Improve default settings

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Add doc

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Update docs

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Thanks clippy

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Thanks cargo fmt

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Update docs

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Do not use HOSTNAME env

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Bump llama.cpp & cuda

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Fix requirements.txt

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Fix fmt

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Enable KQV offload by default

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Remove Ngrok tunneling

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Remove .cargo/config.toml

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Fix Dockerfile

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Add missing cuda prefix

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Handle custom llama.cpp dir

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Cleanup

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Add README.md

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Add HF transfer

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Fix bool args

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Update doc

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Update doc

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

---------

Signed-off-by: Adrien Gallouët <angt@huggingface.co>
Co-authored-by: Morgan Funtowicz <funtowiczmo@gmail.com>
2025-02-14 13:40:57 +01:00

77 lines
2.1 KiB
Plaintext

FROM nvidia/cuda:12.8.0-cudnn-devel-ubuntu24.04 AS deps
ARG llamacpp_version=b4651
ARG llamacpp_cuda=OFF
ARG cuda_arch=75-real;80-real;86-real;89-real;90-real
WORKDIR /opt/src
ENV DEBIAN_FRONTEND=noninteractive
RUN apt update && apt install -y \
clang \
cmake \
curl \
git \
python3-dev \
libssl-dev \
pkg-config \
tar
ADD https://github.com/ggerganov/llama.cpp/archive/refs/tags/${llamacpp_version}.tar.gz /opt/src/
RUN tar -xzf ${llamacpp_version}.tar.gz \
&& cd llama.cpp-${llamacpp_version} \
&& cmake -B build \
-DCMAKE_INSTALL_PREFIX=/usr \
-DCMAKE_INSTALL_LIBDIR=/usr/lib \
-DCMAKE_C_COMPILER=clang \
-DCMAKE_CXX_COMPILER=clang++ \
-DCMAKE_CUDA_ARCHITECTURES=${cuda_arch} \
-DGGML_CUDA=${llamacpp_cuda} \
-DLLAMA_BUILD_COMMON=OFF \
-DLLAMA_BUILD_TESTS=OFF \
-DLLAMA_BUILD_EXAMPLES=OFF \
-DLLAMA_BUILD_SERVER=OFF \
&& cmake --build build --parallel --config Release \
&& cmake --install build
WORKDIR /app
COPY rust-toolchain.toml rust-toolchain.toml
RUN curl -sSf https://sh.rustup.rs | sh -s -- -y --no-modify-path --default-toolchain none
ENV PATH="/root/.cargo/bin:$PATH"
RUN cargo install cargo-chef --locked
FROM deps AS planner
COPY . .
RUN cargo chef prepare --recipe-path recipe.json
FROM deps AS builder
COPY --from=planner /app/recipe.json recipe.json
RUN cargo chef cook \
--recipe-path recipe.json \
--profile release-opt \
--package text-generation-router-llamacpp
COPY . .
RUN cargo build \
--profile release-opt \
--package text-generation-router-llamacpp --frozen
FROM nvidia/cuda:12.8.0-cudnn-runtime-ubuntu24.04
RUN apt update && apt install -y \
python3-venv \
python3-pip
RUN python3 -m venv /venv
ENV PATH="/venv/bin:$PATH"
COPY backends/llamacpp/requirements.txt requirements.txt
RUN pip3 install --no-cache-dir -r requirements.txt
COPY --from=builder /usr/lib/libllama.so /usr/lib/
COPY --from=builder /usr/lib/libggml*.so /usr/lib/
COPY --from=builder /app/target/release-opt/text-generation-router-llamacpp /usr/bin/
ENV HF_HUB_ENABLE_HF_TRANSFER=1
ENTRYPOINT ["text-generation-router-llamacpp"]