pyr0ball bd132851ec fix(orch): tighten VRAM pre-flight to require full max_mb free (not half) ... max_mb // 2 was too loose — Qwen2.5-3B needs ~5.9 GB on an 8 GB card but the threshold only required 3.25 GB free, allowing Ollama to hold 4.5 GB while a load attempt was still dispatched (causing OOM crash). - node_selector: can_fit = free_mb >= service_max_mb (was // 2) - coordinator /start: same threshold fix + updated error message - tests: two new node_selector tests pin the full-ceiling semantics; updated stale docstring in coordinator app test		2026-04-02 16:44:36 -07:00
..
config	feat: add config module and vision router stub	2026-03-25 11:08:03 -07:00
db	feat(orch): replace Ouro/vllm-Docker with generic HF inference server; add ProcessSpec	2026-04-02 15:33:08 -07:00
llm	fix: TTL sweep, immutability, service-scoped release, logger in orch alloc	2026-04-02 12:55:38 -07:00
pipeline	feat: add wizard and pipeline stubs	2026-03-25 11:09:40 -07:00
resources	fix(orch): tighten VRAM pre-flight to require full max_mb free (not half)	2026-04-02 16:44:36 -07:00
tasks	fix(scheduler): join batch worker threads in shutdown()	2026-04-01 11:21:30 -07:00
tiers	fix(core): SQLite timeout=30, INSERT OR IGNORE migrations, parameterize tier unlockables	2026-03-31 10:37:51 -07:00
vision	feat: add config module and vision router stub	2026-03-25 11:08:03 -07:00
wizard	feat: add wizard and pipeline stubs	2026-03-25 11:09:40 -07:00
__init__.py	feat: scaffold circuitforge-core package	2026-03-25 11:02:26 -07:00