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

Downgrade NCCL version from 2.26.5 to 2.25.1 (#4931)

Browse Source 
Signed-off-by: Yiqing Yan <yiqingy@nvidia.com>
This commit is contained in:
Yiqing Yan 2025-06-05 14:03:39 +08:00 committed by GitHub
parent c4c7dd3517
commit f9082a7168
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 9 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.devcontainer/docker-compose.yml
View File

@ -1,7 +1,7 @@
version: "3.9"
services:
tensorrt_llm-dev:
image: urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:pytorch-25.04-py3-x86_64-ubuntu24.04-trt10.10.0.31-skip-tritondevel-202505211401-4539
image: urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:pytorch-25.04-py3-x86_64-ubuntu24.04-trt10.10.0.31-skip-tritondevel-202505292346-4931
network_mode: host
ipc: host

6
docker/common/install_tensorrt.sh
View File

@ -9,9 +9,9 @@ CUDA_VER="12.9" # 12.9.0
# Keep the installation for cuDNN if users want to install PyTorch with source codes.
# PyTorch 2.x can compile with cuDNN v9.
CUDNN_VER="9.9.0.52-1"
# NCCL version 2.26.3 used in the NGC PyTorch 25.04 image but not existing in public.
# Use NCCL version 2.26.5 instead.
NCCL_VER="2.26.5-1+cuda12.9"
# NCCL version 2.26.x used in the NGC PyTorch 25.04 image but has a performance regression issue.
# Use NCCL version 2.25.1 instead.
NCCL_VER="2.25.1-1+cuda12.8"
# cuBLAS version 12.9.0.2 used in the NGC PyTorch 25.04 image but not existing in public.
# Use cuBLAS version 12.9.0.13 instead.
CUBLAS_VER="12.9.0.13-1"

8
jenkins/L0_MergeRequest.groovy
View File

@ -21,10 +21,10 @@ UPLOAD_PATH = env.uploadPath ? env.uploadPath : "sw-tensorrt-generic/llm-artifac
// Container configuration
// available tags can be found in: https://urm.nvidia.com/artifactory/sw-tensorrt-docker/tensorrt-llm/
// [base_image_name]-[arch]-[os](-[python_version])-[trt_version]-[torch_install_type]-[stage]-[date]-[mr_id]
LLM_DOCKER_IMAGE = "urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:pytorch-25.04-py3-x86_64-ubuntu24.04-trt10.10.0.31-skip-tritondevel-202505211401-4539"
LLM_SBSA_DOCKER_IMAGE = "urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:pytorch-25.04-py3-aarch64-ubuntu24.04-trt10.10.0.31-skip-tritondevel-202505211401-4539"
LLM_ROCKYLINUX8_PY310_DOCKER_IMAGE = "urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:cuda-12.9.0-devel-rocky8-x86_64-rocky8-py310-trt10.10.0.31-skip-tritondevel-202505211401-4539"
LLM_ROCKYLINUX8_PY312_DOCKER_IMAGE = "urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:cuda-12.9.0-devel-rocky8-x86_64-rocky8-py312-trt10.10.0.31-skip-tritondevel-202505211401-4539"
LLM_DOCKER_IMAGE = "urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:pytorch-25.04-py3-x86_64-ubuntu24.04-trt10.10.0.31-skip-tritondevel-202505292346-4931"
LLM_SBSA_DOCKER_IMAGE = "urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:pytorch-25.04-py3-aarch64-ubuntu24.04-trt10.10.0.31-skip-tritondevel-202505292346-4931"
LLM_ROCKYLINUX8_PY310_DOCKER_IMAGE = "urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:cuda-12.9.0-devel-rocky8-x86_64-rocky8-py310-trt10.10.0.31-skip-tritondevel-202505292346-4931"
LLM_ROCKYLINUX8_PY312_DOCKER_IMAGE = "urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:cuda-12.9.0-devel-rocky8-x86_64-rocky8-py312-trt10.10.0.31-skip-tritondevel-202505292346-4931"
// TODO: Move common variables to an unified location
BUILD_CORES_REQUEST = "8"

2
jenkins/controlCCache.groovy
View File

@ -1,7 +1,7 @@
import java.lang.InterruptedException
DOCKER_IMAGE = "urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:pytorch-25.04-py3-x86_64-ubuntu24.04-trt10.10.0.31-skip-tritondevel-202505211401-4539"
DOCKER_IMAGE = "urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:pytorch-25.04-py3-x86_64-ubuntu24.04-trt10.10.0.31-skip-tritondevel-202505292346-4931"
def createKubernetesPodConfig(image)
{