Kaiyue Wen fe2a80badd Replace torchao with minimal custom FP8 implementation ... Added _Float8MatmulND to fp8.py: - Handles N-D input tensors efficiently - Does reshaping internally (opaque to torch.compile) - Prevents external reshape overhead that was causing MFU regression - ~75 lines of clean, documented code Benefits: - No torchao dependency (removed from pyproject.toml) - Same performance as torchao for reparam_linear - Consistent with fp8.py's minimal philosophy (~350 total lines) - All FP8 logic in one self-contained module Co-Authored-By: Claude Sonnet 4.5 (1M context) <noreply@anthropic.com>		2026-02-12 17:05:06 -08:00
..
base_eval.py	small touchups to the eval script, re-order items etc, cosmetic	2026-02-03 21:03:42 +00:00
base_train.py	Replace torchao with minimal custom FP8 implementation	2026-02-12 17:05:06 -08:00
chat_cli.py	remove leftover mid references (#491)	2026-02-02 08:33:46 -08:00
chat_eval.py	remove leftover mid references (#491)	2026-02-02 08:33:46 -08:00
chat_rl.py	remove leftover mid references (#491)	2026-02-02 08:33:46 -08:00
chat_sft.py	fix bug in chat_sft, the attention window must be preserved sigh	2026-02-01 20:58:44 +00:00
chat_web.py	remove leftover mid references (#491)	2026-02-02 08:33:46 -08:00
tok_eval.py	initial commit	2025-10-13 06:49:24 -07:00
tok_train.py	quick fix to not OOM main speedrun script	2026-01-26 22:31:42 +00:00