Files
kuberay-images/dockerfiles
Billy D. 8adaef62a2
Some checks failed
Build and Push Images / determine-version (push) Successful in 6s
Build and Push Images / build (Dockerfile.ray-worker-rdna2, rdna2) (push) Has been cancelled
Build and Push Images / build (Dockerfile.ray-worker-strixhalo, strixhalo) (push) Has been cancelled
Build and Push Images / Release (push) Has been cancelled
Build and Push Images / Notify (push) Has been cancelled
Build and Push Images / build (Dockerfile.ray-worker-intel, intel) (push) Has been cancelled
Build and Push Images / build (Dockerfile.ray-worker-nvidia, nvidia) (push) Has been cancelled
fix(strixhalo): remove apt-get layer that corrupts vendor hipcc
The vendor image (rocm/pytorch:rocm7.0.2) ships all needed runtime
packages. Any apt-get install triggers ROCm repo dependency resolution
that upgrades vendor hipcc 1.1.1.70002 to Ubuntu's 5.7.1, whose
hipconfig.pl reports HIP version 0.0.0 → cmake can't find HIP.

Changes:
- Remove entire apt-get layer (git, ccache, runtime libs all pre-installed)
- Keep only ray user creation from that RUN block
- Add detailed comments explaining why apt-get must never be used

Combined with cmake<4 (downgrade from 4.0.0) and HIP_ROOT_DIR=/opt/rocm
from prior commits, this produces a successful build (attempt 5).

Verified: torch 2.9.1+rocm7.0.2 (vendor), vllm 0.15.2.dev0 (source-built)
2026-02-09 18:24:50 -05:00
..
2026-02-09 10:56:51 -05:00