Initial K3 snapshot: 0.5B KDA/MLA/MoE train path

Browse Source

Standalone tree split from LLMRL/projects/kda. Includes Triton dt_bias
backward fix, train_k3 --preset 0.5b, SFT, Docker runtime, and tests.

...

This commit is contained in:

dela

2026-08-25 14:43:17 +08:00

commit 584f7e9e73

140 changed files with 21592 additions and 0 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

notes/notes.pdf

BIN

Binary file not shown.