nanochat

9 Commits 4 Branches 0 Tags 77 MiB

Author	SHA1	Message	Date
google-labs-jules[bot]	08c628cb83	feat: Add ROCm and device-agnostic support This change adds support for ROCm and makes the codebase device-agnostic, allowing it to run on different hardware backends including ROCm, CUDA, and CPU. The key changes are: - Modified `pyproject.toml` to use ROCm-compatible PyTorch wheels and added the `pytorch-triton-rocm` dependency. - Refactored `nanochat/common.py` to dynamically detect the available hardware and set the device and distributed backend accordingly. - Updated all training, evaluation, and inference scripts to be device-agnostic, removing hardcoded CUDA references. - Adapted `speedrun.sh` for single-device execution by replacing `torchrun` with `python`. - Updated `nanochat/report.py` to provide more generic GPU information.	2025-10-14 05:07:30 +00:00
Andrej	dd6ff9a1cc	fix bug in fallback case of find_largest_model Fix: Handle missing d<number> model tags in find_largest_model ty	2025-10-13 14:38:34 -07:00
Mirza-Samad-Ahmed-Baig	afaa5b4c90	Fix: Handle missing d<number> model tags in find_largest_model	2025-10-14 00:24:07 +03:00
Andrej	5fd0b13886	Merge pull request #2 from epoyraz/patch-1 Update README.md	2025-10-13 10:10:15 -07:00
Enes Poyraz	6a795baf27	Update README.md fix typos	2025-10-13 18:40:12 +02:00
Andrej	626bd3e260	Add image of the WebUI to readme	2025-10-13 08:03:00 -07:00
karpathy	da96b46565	update link to the new discussion	2025-10-13 07:42:09 -07:00
karpathy	a53833d04f	add nanochat logo png	2025-10-13 06:59:59 -07:00
karpathy	3a5e0bc50b	initial commit	2025-10-13 06:49:24 -07:00