mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
74cc9e26ff
* infra: install Triton in the base image Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com> * install Triton from the base image Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com> * update base image Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com> * Address review comments Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com> * update base image Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com> * waive test Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com> --------- Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>
33 lines
878 B
YAML
33 lines
878 B
YAML
version: "3.9"
|
|
services:
|
|
tensorrt_llm-dev:
|
|
image: urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:pytorch-25.03-py3-x86_64-ubuntu24.04-trt10.9.0.34-skip-devel-202504250100-3759
|
|
network_mode: host
|
|
ipc: host
|
|
|
|
# For GPU usage and profiling
|
|
cap_add:
|
|
- SYS_PTRACE
|
|
- SYS_ADMIN
|
|
security_opt:
|
|
- seccomp:unconfined
|
|
|
|
# Delete this section if you don't have a GPU.
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: "all"
|
|
capabilities: [gpu]
|
|
|
|
volumes:
|
|
- ..:/workspaces/tensorrt_llm:cached
|
|
|
|
environment:
|
|
- CCACHE_DIR=/workspaces/tensorrt_llm/cpp/.ccache
|
|
- CCACHE_BASEDIR=/workspaces/tensorrt_llm
|
|
|
|
# Overrides default command so things don't shut down after the process ends.
|
|
command: /bin/sh -c "while sleep 1000; do :; done"
|