fix(halo): drop speculative HSA_OVERRIDE_GFX_VERSION from llama-server

Was set defensively without knowing the actual GPU arch; if ROCm
supports the card natively, the override is at best a no-op and at
worst masks the real arch. Add it back with the right value if the
service actually fails to detect the GPU.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Harald Hoyer 2026-05-05 10:41:05 +02:00
parent b11e5c8356
commit da88a9b2d6

View file

@ -13,7 +13,6 @@
environment = { environment = {
HOME = "%S/llama-server"; HOME = "%S/llama-server";
HF_HOME = "%S/llama-server"; HF_HOME = "%S/llama-server";
HSA_OVERRIDE_GFX_VERSION = lib.mkDefault "11.0.0";
}; };
serviceConfig = { serviceConfig = {