ViperEkura/AstrAI
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
786 Commits 1 Branch 14 Tags
1d57588d2795c981c31ac82c54f3f4155dcc7d82
Commit Graph
4 Commits
Author SHA1 Message Date
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 00c2c80c8f feat: unify Docker training configuration in YAML 2026-08-19 14:04:35 +08:00
ViperEkura a6c6a54ace feat: read host training vars from YAML infra section 
- scripts/train.sh load_infra() parses the top-level infra: section of TRAIN_CONFIG_FILE
- exports TRAIN_JOB_NAME/DATA/MODEL/CHECKPOINT_DIR/TRAIN_GPU_COUNT/CUDA_VISIBLE_DEVICES
- infra overrides .env.train via compose interpolation precedence; keys absent fall back
- train.yaml is now the single per-job config: host mounts, GPU filter, and hyperparameters
- requires host python3 with PyYAML when TRAIN_CONFIG_FILE is set; errors fail fast
- docs: docker-training.md documents the infra overrides and precedence
 2026-08-19 01:27:57 +08:00
ViperEkura da6d94492d fix: parse yaml floats with yaml 1.2 schema 
- register yaml 1.2 float resolver so scientific notation (2e-5) becomes float, not str
- replaces the decimal-point workaround in train configs
- add containerized training doc under docs/developer
 2026-08-13 23:28:06 +08:00