104 Commits

Author	SHA1	Message	Date
Andrej Karpathy	01fb290f53	allow multiple GPUs to do inference in a data parallel way	2025-10-15 19:12:19 +00:00
Bhaskar	02440f670d	fix: return inf instead of crashing when evaluate_bpb has zero total_bytes ... Edge case: all tokens are special tokens or ignored Return infinity to indicate no meaningful bytes were processed	2025-10-14 17:21:11 +05:30
Mirza-Samad-Ahmed-Baig	afaa5b4c90	Fix: Handle missing d<number> model tags in find_largest_model	2025-10-14 00:24:07 +03:00
karpathy	3a5e0bc50b	initial commit	2025-10-13 06:49:24 -07:00