-
Notifications
You must be signed in to change notification settings - Fork 0
Pull requests: Approaching-AI/AIMA
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
openclaw sync: preflight-probe the AIMA proxy and warn loudly if unreachable
#91
opened Jun 12, 2026 by
rjckkkkk
Collaborator
Loading…
Auto-wire llama.cpp --mmproj for VL models (zero-config vision)
#90
opened Jun 11, 2026 by
rjckkkkk
Collaborator
Loading…
Add Qwen2.5-VL-3B-Instruct model knowledge (vlm + verified perf)
#89
opened Jun 11, 2026 by
rjckkkkk
Collaborator
Loading…
Hide the deploy launcher console window on Windows
#88
opened Jun 11, 2026 by
rjckkkkk
Collaborator
Loading…
Fix native deploy readiness: deploy.apply returned a name status lookup couldn't find
#87
opened Jun 11, 2026 by
rjckkkkk
Collaborator
Loading…
Launch native engines from AIMA_ENGINE_DIR (scanned ⇒ launchable)
#86
opened Jun 10, 2026 by
rjckkkkk
Collaborator
Loading…
Add AMD ROCm/HIP Windows llama.cpp engine (auto-download on Strix Halo)
#85
opened Jun 9, 2026 by
rjckkkkk
Collaborator
Loading…
fix(external): don't list AIMA's own deployment backend (llama.cpp :8080) as an external service
#83
opened Jun 9, 2026 by
rjckkkkk
Collaborator
Loading…
feat(model): mark speculative draft heads (DFlash/MTP) as non-standalone
#82
opened Jun 9, 2026 by
rjckkkkk
Collaborator
Loading…
Add Strix Halo llama.cpp GGUF model knowledge (aliases + verified perf)
#81
opened Jun 8, 2026 by
rjckkkkk
Collaborator
Loading…
Discover off-PATH native engine binaries via AIMA_ENGINE_DIR
#80
opened Jun 8, 2026 by
rjckkkkk
Collaborator
Loading…
Discover models across all drives; group split GGUF shards
#79
opened Jun 8, 2026 by
rjckkkkk
Collaborator
Loading…
Detect Windows hardware via CIM, add AMD GPU detection
#78
opened Jun 8, 2026 by
rjckkkkk
Collaborator
Loading…
ProTip!
Mix and match filters to narrow down what you’re looking for.