Skip to content
hal0

ROCm vs vulkan_radv

knowledge base · runtime & backends·reviewed 2026-08-09·suggest an edit ↗

A Strix Halo box can serve the same model two different ways: through ROCm (AMD’s compute stack) or through vulkan_radv (Mesa’s open-source Vulkan driver). hal0 picks a lane per slot, and which one is right depends on what you’re optimizing for.

The short version

Section titled “The short version”
  • ROCm is faster on prefill and generally the better default when it builds cleanly for your kernel/driver combination.
  • vulkan_radv needs nothing beyond the in-tree Mesa driver — no userspace ROCm stack to install or pin — at the cost of slower prefill on long contexts.
  • Both lanes read from the same GTT pool and the same model weights on disk; switching lanes doesn’t change what’s resident.

Telling which one you’re on

Section titled “Telling which one you’re on”
Terminal window
hal0 slots --verbose

The lane column reports rocm or vulkan_radv per slot. The leaderboard also breaks out decode/prefill by lane per model, so you can see the actual gap for your model rather than trusting a rule of thumb.

When to reach for Vulkan

Section titled “When to reach for Vulkan”

ROCm’s kernel and firmware requirements move faster than distro packaging. If a ROCm build won’t come up on your kernel version, hal0 falls back to vulkan_radv rather than failing to serve — that fallback is deliberate, not a bug. It’s also the simpler starting point if you’re still validating that the iGPU is visible at all before debugging a ROCm-specific issue.

Section titled “Related”