From 09fdbe24d4335acb00a29292f4fea8b62589355b Mon Sep 17 00:00:00 2001 From: Jose Rodriguez Date: Sat, 20 Dec 2025 13:45:23 -0800 Subject: [PATCH] Use --extra gpu when building rustbpe with maturin --- run1000.sh | 2 +- speedrun.sh | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/run1000.sh b/run1000.sh index 58ee3bc..ccaac7d 100644 --- a/run1000.sh +++ b/run1000.sh @@ -18,7 +18,7 @@ fi python -m nanochat.report reset curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y source "$HOME/.cargo/env" -uv run maturin develop --release --manifest-path rustbpe/Cargo.toml +make rust-dev-gpu curl -L -o $NANOCHAT_BASE_DIR/identity_conversations.jsonl https://karpathy-public.s3.us-west-2.amazonaws.com/identity_conversations.jsonl # train tokenizer on ~4B characters and kick off download of the rest for pretraining diff --git a/speedrun.sh b/speedrun.sh index 501c176..b262e80 100644 --- a/speedrun.sh +++ b/speedrun.sh @@ -53,7 +53,7 @@ curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y source "$HOME/.cargo/env" # Build the rustbpe Tokenizer -uv run maturin develop --release --manifest-path rustbpe/Cargo.toml +make rust-dev-gpu # Download the first ~2B characters of pretraining dataset # look at dev/repackage_data_reference.py for details on how this data was prepared