3 Commits

Author	SHA1	Message	Date
Andrej Karpathy	2ff7d51252	integrate Flash Attention 3. +9% tok_per_sec for d12 with ctx even as low as 2048 out of the box nice. also, ready to tune windows huge	2026-01-11 20:33:19 +00:00
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
Andrej Karpathy	baf0b3fdda	also add a test that failed before the fix and passes now with the fix for kv cache resize	2025-10-28 16:54:17 +00:00