Together AI Blog company blog
AdapTive-LeArning Speculator System (ATLAS): Faster LLM inference
LLM inference that gets faster as you use it. Our runtime-learning accelerator adapts continuously to your workload, delivering 500 TPS on DeepSeek-V3.1, a 4x speedup over baseline performance without manual tuning.
- Points
- 198
- HN comments
- 47
- Submissions
- 1
- Cited by
- 0 commenters
AI & Machine LearningSystems & Performance2025
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Oct 12, 2025 | AdapTive-LeArning Speculator System (ATLAS): Faster LLM inference by alecco | 198 | 47 |
