kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

update triton image

Browse Source 
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
This commit is contained in:
Xiwen Yu 2025-08-06 23:49:56 +08:00
parent bee1df9479
commit 97a3788dcf
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docker/Dockerfile.multi
View File

@ -1,8 +1,8 @@
# Multi-stage Dockerfile
ARG BASE_IMAGE=gitlab-master.nvidia.com:5005/dl/dgx/pytorch
ARG TRITON_IMAGE=nvcr.io/nvidia/tritonserver
ARG TRITON_IMAGE=gitlab-master.nvidia.com:5005/dl/dgx/tritonserver
ARG BASE_TAG=25.08-py3.32224057-base
ARG TRITON_BASE_TAG=25.06-py3
ARG TRITON_BASE_TAG=25.08-RC-py3.32078257
ARG DEVEL_IMAGE=devel
FROM ${BASE_IMAGE}:${BASE_TAG} AS base

2
jenkins/Build.groovy
View File

@ -447,7 +447,7 @@ def runLLMBuild(pipeline, buildFlags, tarName, is_linux_x86_64)
def llmPath = sh (script: "realpath ${LLM_ROOT}",returnStdout: true).trim()
// TODO: Remove after the cmake version is upgraded to 3.31.8
// Get triton tag from docker/dockerfile.multi
def tritonShortTag = sh(script: "${LLM_ROOT}/jenkins/scripts/get_triton_tag.sh ${LLM_ROOT}", returnStdout: true).trim()
def tritonShortTag = "r25.08"
sh "cd ${LLM_ROOT}/triton_backend/inflight_batcher_llm && mkdir build && cd build && cmake .. -DTRTLLM_DIR=${llmPath} -DTRITON_COMMON_REPO_TAG=${tritonShortTag} -DTRITON_CORE_REPO_TAG=${tritonShortTag} -DTRITON_THIRD_PARTY_REPO_TAG=${tritonShortTag} -DTRITON_BACKEND_REPO_TAG=${tritonShortTag} -DUSE_CXX11_ABI=ON && make -j${BUILD_JOBS} install"
// Step 3: packaging wheels into tarfile