ViperEkura
056c1382ff
docs: sync all documentation with current codebase
- remove GenerationRequest and generate_with_request references (class deleted)
- document cuda>flash>torch default priority and FlashAttnBackend
- add ASTR_BACKEND env var to backend docs, TorchNativeBackend (default) → (fallback)
- fix JsonlStore transform routing → DatasetFactory ownership
- fix CudaBackend fallback chain description (FlashAttn → TorchNative)
- add FlashAttnBackend to architecture strategy table
- add router_stats to DecoderOutput/FFNOutput TypedDict diagrams
- add decode_o_part/ml_part/decode_out to KVCache diagram
- add --append_eos/--no-append_eos to IFD evaluation parameter table
- update get-started CUDA kernel note (no longer requires explicit attn_backend activation)
- fix python -m scripts.tools.server (no __init__.py) → direct script call
2026-08-07 23:52:27 +08:00
..
2026-08-02 07:39:24 +08:00
2026-08-07 23:52:27 +08:00
2026-08-07 23:52:27 +08:00
2026-08-02 07:39:24 +08:00
2026-08-02 07:39:24 +08:00
2026-08-03 20:54:40 +08:00