Commit Graph
3 Commits
Author SHA1 Message Date
ViperEkura ba8beb81be fix: serve and train reuse the built image and expose GPUs correctly
- serve.sh/train.sh no longer pass --build on up/run; the build subcommand is the only path that rebuilds
- compose services pin image: astrai:latest so run reuses the existing image instead of triggering a rebuild
- runtime parsers leave CUDA_VISIBLE_DEVICES unset for gpu.devices: all; an empty string hid every GPU inside the container
- server service reserves count: all GPUs so CUDA_VISIBLE_DEVICES performs the only filtering, matching the trainer
- wrapper compose() strips an empty host CUDA_VISIBLE_DEVICES before invoking docker compose
2026-08-27 12:22:02 +08:00
ViperEkura 10fec8dca1 docs: fix stale docs and align with code
- update cuda_kernels layout, arch flags, and add FP8 section
- fix install docs: kernels auto-build when nvcc + CUDA detected
- mark ignored OpenAI request params and complete KVCache fields
- add docker docs to indexes and astrai.optim to module overview
- refresh document update timestamps
2026-08-23 14:23:28 +08:00
ViperEkura cb21af38ba feat: unify Docker serving configuration in YAML
- Add server.py --config serve.yaml; explicit CLI flags override YAML
- Add scripts/serve.sh and serve_runtime.py for the Compose lifecycle
- Template server/cpu ports and param mounts in docker-compose.yml
- Document schema in docs/developer/docker-serving.md and params guide
- Add tests for runtime parsing and server CLI merge logic
2026-08-21 23:16:45 +08:00