fix(compose): request NVIDIA compute capability (#11990)

The legacy NVIDIA device reservation requests utility without compute.
Docker derives driver capabilities from that list, leaving CUDA libraries
unavailable even when monitoring works.

Include compute in the legacy example and clarify the matching docs.

Assisted-by: Codex:GPT-6

Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com>
This commit is contained in:
localai-org-maint-botandlocalai-org-maint-bot authored and GitHub committed 2026-09-27 21:07:08 +02:00
1 parent c6f1e96a7d
commit 1b1bd0f069
3 files changed
+12 -5

No files matched your search

+2 -1
View File
@@ -59,6 +59,7 @@ services:
# capabilities: [gpu, utility]
#
# For legacy NVIDIA driver (for older NVIDIA Container Toolkit):
# Request compute for CUDA libraries (libcuda.so.1) and utility for NVML.
# environment:
# NVIDIA_DRIVER_CAPABILITIES: "compute,utility"
# init: true
@@ -68,7 +69,7 @@ services:
# devices:
# - driver: nvidia
# count: 1
# capabilities: [gpu, utility]
# capabilities: [gpu, compute, utility]
## Uncomment for PostgreSQL-backed knowledge base (see Agents docs)
# postgres: