kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-13 22:18:36 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Add tritonrelease container (#4455)

Browse Source 
* Add tritonrelease container

Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>

* Review comments

Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>

* Update docker/Makefile

Co-authored-by: Martin Marciniszyn Mehringer <11665257+MartinMarciniszyn@users.noreply.github.com>
Signed-off-by: Iman Tabrizian <10105175+Tabrizian@users.noreply.github.com>

---------

Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
Signed-off-by: Iman Tabrizian <10105175+Tabrizian@users.noreply.github.com>
Co-authored-by: Martin Marciniszyn Mehringer <11665257+MartinMarciniszyn@users.noreply.github.com>
This commit is contained in:
Iman Tabrizian 2025-05-21 23:47:50 -04:00 committed by GitHub
parent 2898d268f9
commit e741d2b8d0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 18 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
docker/Dockerfile.multi
View File

@ -161,3 +161,17 @@ ARG GIT_COMMIT
ARG TRT_LLM_VER
ENV TRT_LLM_GIT_COMMIT=${GIT_COMMIT} \
TRT_LLM_VERSION=${TRT_LLM_VER}
FROM wheel AS tritonbuild
WORKDIR /src/tensorrt_llm
RUN pip install /src/tensorrt_llm/build/tensorrt_llm*.whl
COPY ./triton_backend/ ./triton_backend/
RUN bash ./triton_backend/inflight_batcher_llm/scripts/build.sh
FROM release AS tritonrelease
WORKDIR /app/tensorrt_llm
COPY ./triton_backend/ ./triton_backend/
COPY --from=tritonbuild /opt/tritonserver/backends/tensorrtllm /opt/tritonserver/backends/tensorrtllm

3
docker/Makefile
View File

@ -148,6 +148,9 @@ endif
devel_%: STAGE = devel
tritondevel_%: STAGE = tritondevel
tritonrelease_%: STAGE = tritonrelease
tritonrelease_%: DEVEL_IMAGE = tritondevel
tritonrelease_run: WORK_DIR = /app/tensorrt_llm
wheel_%: STAGE = wheel
wheel_run: WORK_DIR = /src/tensorrt_llm

2
triton_backend/inflight_batcher_llm/CMakeLists.txt
View File

@ -24,7 +24,7 @@
cmake_minimum_required(VERSION 3.17)
include(${CMAKE_CURRENT_SOURCE_DIR}/cmake/modules/set_ifndef.cmake)
set_ifndef(TRTLLM_DIR ${CMAKE_CURRENT_SOURCE_DIR}/../tensorrt_llm)
set_ifndef(TRTLLM_DIR ${CMAKE_CURRENT_SOURCE_DIR}/../../)
include_directories(${TRTLLM_DIR} ${TRTLLM_DIR}/cpp/include)