localai-org-maint-bot 3f9ffb1af6 feat(gallery): add Spark-X2.5-4B variants ...

Add Q4_K_M, Q6_K, and Q8_0 builds with embedded Jinja templates.
The pinned llama.cpp revision supports the Spark-X2.5 architecture.
Document installation and use a 32K context default to limit memory.

Assisted-by: Codex:gpt-6

2026-09-08 08:08:20 +00:00

..

advanced

fix(diffusers): auto-detect CUDA instead of defaulting to CPU (#11891)

2026-09-08 08:44:35 +02:00

features

feat(gallery): add Spark-X2.5-4B variants

2026-09-08 08:08:20 +00:00

getting-started

Update containers.md to fix podman image qualification (#11749)

2026-09-06 12:45:56 +02:00

operations

docs: fix dead anchors and a dead section link (#11885)

2026-09-05 23:47:13 +02:00

reference

docs: correct documented env var and CLI flag names (#11886)

2026-09-05 23:49:10 +02:00

_index.md

…

faq.md

…

integrations.md

docs(integrations): add Distribution Packages section (#11904)

2026-09-07 16:36:58 +02:00

overview.md

…

whats-new.md

…