Together AI Drops Megakernels for New Compiler with 28% Speedup on B200
Together AI announced it has abandoned megakernels in favor of Together Compiler, an AI agent-based auto-tuning system that boosts throughput up to 2.6x and delivers 28% faster performance on B200 GPUs.
2026-11-17 ~ 2026-11-17 · 2 related posts
- Episode 1: Together AI Launches TKCC, an Agent-Driven Continuously Compiling Inference Optimizer(2026-11-05, 28 posts)
- Episode 2: Together AI launches agentic continual compiler TKCC for faster inference(2026-11-05, 4 posts)
- Episode 3: Together Compiler boosts Kimi K3 throughput up to 2.7x(2026-11-10, 2 posts)
- Episode 4: Together AI Drops Megakernels for New Compiler with 28% Speedup on B200(2026-11-17, 2 posts)
- Together Deleted Its Megakernels: AI Agents Tune Inference 28% Faster on B200 — togethercompute · 2026-11-17
- Together explains why it dropped megakernels for agent-tuned inference compilation — togethercompute · 2026-11-17