Together Compiler: agent-driven continual compilation for AI inference
togethercompute · x · 2026-11-12
Together unveils Together Compiler (TKCC), introducing "Polymorphic Inference" — an agent-driven approach to continual inference compilation. The workflow: run the model end to end, find bottlenecks, then let the model fix them.
Key context from the announcement:
- Manual optimization can't scale: none of the top-10 open-source LLMs on OpenRouter share an architecture, and Together serves many trillions of tokens daily across thousands of customers with wildly different traffic shapes (batch size, sequence length, MoE imbalance, attention sparsity)
- Hardware diversity adds more regimes: H100, B200, B300, NVL72, VR, Groq each need distinct strategies
- Agentic systems are theoretically ideal for this search problem but today are bottlenecked by experiment speed; TKCC is billed as the first truly continual optimization system
Also announced: Together Post-Training, Together Link (run open models inside existing harnesses), and on-demand B200s on Together GPU Clusters.
Related event: Together Compiler boosts Kimi K3 throughput up to 2.7x(2 posts)→
More from coding & agent
- Pokee AI showcases enterprise agents with 10M-token context at NexTech Week Japan — Kyrannio · 2026-11-12
- 'AGI is three months away' has been said for two years: Diogo's 10 sharpest quotes on software — TheTuringPost · 2026-11-12
- A 4-layer architecture for wiring Claude into a company's live operations — aryanXmahajan · 2026-11-12
- "Idle compaction by default is stochastic lobotomy": a one-line takedown of auto context compaction — generativist · 2026-11-12
- Fable 5.2 can build production software unattended overnight—but Opus still wins for writing — every · 2026-11-12
- Nace.AI launches Drex for Document Processing, claiming 0.834 Parse Index across 12 parsers — rohanpaul_ai · 2026-11-12