nanochat/tests
Andrej Karpathy 8f979a8bda fix: sample first token independently for each row in multi-sample generation
Previously, when generating multiple samples (num_samples > 1), the first
token after prefill was sampled once and broadcast to all rows, causing
all samples to start identically. Now the prefill logits are expanded to
num_samples and sampled independently for each row.

Also simplified the generation loop by moving the forward pass to the end
of the loop, eliminating the first_iteration flag and if/else branching.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-28 04:52:13 +00:00
..
test_engine.py fix: sample first token independently for each row in multi-sample generation 2025-12-28 04:52:13 +00:00
test_rustbpe.py Replace speedup assertion with warning in batch_encode test 2025-12-28 04:10:49 +00:00