Repository navigation

Add adopt-only llama.cpp engine and distributed inference proxy - #18

Closed

agenticocho wants to merge 7 commits into

NVIDIA:developfrom

agenticocho:ocho/llama-cpp-engine

Closed

Add adopt-only llama.cpp engine and distributed inference proxy#18
agenticocho wants to merge 7 commits into
NVIDIA:developfrom
agenticocho:ocho/llama-cpp-engine

Commits on Sep 4, 2026
- feat(engine-manager): add adopt-only llama.cpp manifest
  Chilly
  committed
  08f5380
- feat(proxy): add llama.cpp inference router
  Chilly
  committed
  6560456
- feat: integrate llama.cpp proxy with UI broker
  Chilly
  committed
  b8e817a
- fix: tolerate closed stdout during shutdown
  Chilly
  committed
  8f6add8
Commits on Sep 5, 2026
- feat: expose llama.cpp as a configurable Desktop engine
  Chilly
  committed
  428e2c2
- fix: compile Electron renderer before packaging
  Chilly
  committed
  2d689ab
- fix: expose configuration for external llama.cpp
  Chilly
  committed
  4a671fe