Skip to content

LLM inference in C/C++

C++ ggml

musa: build the docker images from the PH1 MUSA SDK image (#29481)

R0CKSTAR694ec235484b
diff --git a/.devops/musa.Dockerfile b/.devops/musa.Dockerfile
index d30a70bb36..33ac6bb82d 100644
--- a/.devops/musa.Dockerfile
+++ b/.devops/musa.Dockerfile
@@ -1,10 +1,9 @@
ARG UBUNTU_VERSION=22.04
# This needs to generally match the container host's environment.
-ARG MUSA_VERSION=rc4.3.0
# Target the MUSA build image
-ARG BASE_MUSA_DEV_CONTAINER=docker.io/mthreads/musa:${MUSA_VERSION}-devel-ubuntu${UBUNTU_VERSION}-amd64
+ARG BASE_MUSA_DEV_CONTAINER=registry.mthreads.com/mcconline/inference/pytorch:2.9.1.post1-py3.10-musa5.2.0-mp31-devel-ubuntu${UBUNTU_VERSION}-amd64
-ARG BASE_MUSA_RUN_CONTAINER=docker.io/mthreads/musa:${MUSA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}-amd64
+ARG BASE_MUSA_RUN_CONTAINER=${BASE_MUSA_DEV_CONTAINER}
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
diff --git a/docs/docker.md b/docs/docker.md
index b1c6c1f6f9..8712fa9f04 100644
--- a/docs/docker.md
+++ b/docs/docker.md
@@ -123,7 +123,7 @@ You may want to pass in some different `ARGS`, depending on the MUSA environment
The defaults are:
-- `MUSA_VERSION` set to `rc4.3.0`
+- the base image is the MUSA 5.2.0 image from the Moore Threads registry
The resulting images, are essentially the same as the non-MUSA images: