huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-24 08:22:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

Build faster

Browse Source 
Signed-off-by: Adrien Gallouët <angt@huggingface.co>
This commit is contained in:
Adrien Gallouët 2025-02-14 11:54:59 +00:00
parent ec35976f82
commit bda39e42c2
No known key found for this signature in database
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
Dockerfile_llamacpp
View File

@ -48,11 +48,11 @@ FROM deps AS builder
COPY --from=planner /app/recipe.json recipe.json
RUN cargo chef cook \
--recipe-path recipe.json \
--profile release-opt \
--profile release \
--package text-generation-router-llamacpp
COPY . .
RUN cargo build \
--profile release-opt \
--profile release \
--package text-generation-router-llamacpp --frozen
FROM nvidia/cuda:12.8.0-cudnn-runtime-ubuntu24.04
@ -69,7 +69,7 @@ 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/
COPY --from=builder /app/target/release/text-generation-router-llamacpp /usr/bin/
ENV HF_HUB_ENABLE_HF_TRANSFER=1