What's Changed

• Adding comparison for different fp8 matmuls by @drisspg in #36
• Fixes device-tma kernel by @drisspg in #37
• Update benchmarks by @drisspg in #39
• hacking by @drisspg in #41
• Option to use torch.distributed.breakpoint in nan checker by @danielvegamyhre in #46
• update by @drisspg in #47
• remove examples by @drisspg in #43
• misc by @drisspg in #44
• tweaks by @drisspg in #48
• Fix release by @drisspg in #51
• update by @drisspg in #52

New Contributors

• @danielvegamyhre made their first contribution in #46

Full Changelog: v0.0.1...v0.0.2